Method and device for predicting drought risk of watershed and electronic equipment

Abstract

The embodiment of the invention provides a drainage basin drought risk prediction method and device and electronic equipment, and belongs to the technical field of drought prediction. The drainage basin drought risk prediction method comprises the following steps: acquiring a current circulation parameter of a to-be-predicted drainage basin, a historical predicted value of a target meteorological index of the to-be-predicted drainage basin in a past preset time period and a historical climate scene label corresponding to the target meteorological index; determining a current prediction value of the target meteorological index of the to-be-predicted drainage basin; based on a preset index dynamic weight determination model, determining a target dynamic weight corresponding to the target meteorological index according to the historical predicted value of the target meteorological index and the historical climate scene label; according to the current predicted value of the target meteorological index and the target dynamic weight, determining a drought index of the to-be-predicted drainage basin; and determining a target drought risk probability of the to-be-predicted drainage basin according to the drought index. The method can improve the prediction accuracy of the drainage basin drought risk.

Description

Technical Field

[0001] The present invention relates to the technical field of drought prediction, and in particular to a method, device and electronic equipment for predicting drought risk in a watershed. Background Art

[0002] Against the backdrop of global warming, extreme drought events are occurring frequently in river basins (such as the Yangtze River Basin). Therefore, predicting drought risk in river basins is crucial. Existing technologies generally use the Standardized Precipitation Index (SPI) to predict drought risk in river basins. However, these technologies are not very accurate in predicting drought risk in river basins and cannot meet the needs of new power systems for preventing and controlling secondary disasters such as drought-induced wildfires. Therefore, existing technologies suffer from low accuracy in predicting drought risk in river basins. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a method, device, electronic device, storage medium and computer program product for predicting watershed drought risk, so as to solve the problem of low accuracy in predicting watershed drought risk in the prior art.

[0004] To achieve the above objectives, the first embodiment of the present application provides a method for predicting drought risk in a river basin, the method comprising:

[0005] Obtain the current circulation parameters of the basin to be predicted, the historical forecast values ​​of the target meteorological index of the basin to be predicted within the past preset time period, and the historical climate scenario labels corresponding to the target meteorological indexes. The target meteorological indices include the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream.

[0006] Determine the current forecast value of the target meteorological index of the basin to be predicted based on the current circulation parameters;

[0007] Based on the preset index dynamic weight determination model, the target dynamic weight corresponding to the target meteorological index is determined according to the historical forecast value of the target meteorological index and the historical climate scenario label;

[0008] Determine the drought index of the basin to be predicted based on the current predicted value of the target meteorological index and the target dynamic weight;

[0009] Based on the drought index, determine the target drought risk probability of the basin to be predicted.

[0010] In the embodiment of the present application, the target dynamic weight includes the weight of the eastward extension index of the South Asian high pressure, the weight of the westward extension index of the western Pacific subtropical high pressure, and the weight of the northward movement index of the East Asian subtropical westerly jet stream. The drought index of the basin to be predicted is determined based on the current data of the target meteorological index and the target dynamic weight, including the following formula:

[0011] EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|)

[0012] Among them, EDI is the drought index, α is the weight of the eastward extension index of the South Asian high pressure, SHI is the eastward extension index of the South Asian high pressure, β is the weight of the westward extension index of the western Pacific subtropical high pressure, WPI is the westward extension index of the western Pacific subtropical high pressure, JNI is the northward movement index of the East Asian subtropical westerly jet, and γ is the weight of the northward movement index of the East Asian subtropical westerly jet.

[0013] In an embodiment of the present application, determining the drought risk probability of the basin to be predicted based on the drought index includes: determining a target drought index interval corresponding to the drought index; and determining the target drought risk probability of the basin to be predicted based on the target drought index interval based on the correspondence between the predetermined drought index interval and the drought risk probability.

[0014] In the embodiment of the present application, the current circulation parameters include the current longitude value of the eastern boundary of the South Asian high pressure and the current geopotential height value of the South Asian high pressure. The current predicted value of the target meteorological index of the basin to be predicted is determined based on the current circulation parameters, including determining according to the following formula:

[0015]

[0016] Among them, SHI is the index of the eastward extension of the South Asian high pressure, λ east is the longitude value of the eastern boundary of the current South Asian high pressure, is the average of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, σ east is the standard deviation of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, Z 200hPa(i,j) It is the current South Asian high potential height value at each preset position on the preset pressure layer. It is the average value of the current South Asian high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

[0017] In the embodiment of the present application, the current circulation parameters include the current longitude value of the western boundary of the western Pacific subtropical high pressure and the current geopotential height value of the western Pacific subtropical high pressure. According to the current circulation parameters, the current predicted value of the target meteorological index of the basin to be predicted is determined, including determining according to the following formula:

[0018]

[0019] Wherein, WPI is the westward extension index of the western Pacific subtropical high pressure, λ westis the longitude of the western boundary of the current western Pacific subtropical high pressure, is the average of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, σ west is the standard deviation of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, Z 200hPa(i,j) is the current geopotential height value of the western Pacific subtropical high pressure at each preset location on the preset pressure layer, It is the average value of the current western Pacific subtropical high potential height values ​​of multiple preset locations on the preset pressure layer, i is the longitude value of the preset location, j is the latitude value of the preset location, N is the number of preset locations, the longitude value of the preset location ranges from a to b, and the latitude value of the preset location ranges from c to d.

[0020] In the embodiment of the present application, the current circulation parameters include the latitude value of the current maximum zonal wind speed axis at the current moment and the current maximum zonal wind speed at the current moment. The current predicted value of the target meteorological index of the basin to be predicted is determined based on the current circulation parameters, including determining according to the following formula:

[0021]

[0022] Among them, JNI is the index of the northward movement of the East Asian subtropical westerly jet stream, φ axis is the latitude of the axis of the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, σ axis is the standard deviation of the latitude values ​​of the historical maximum zonal wind speed axis within the preset historical time period, U max is the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speeds within the preset historical time period, σ max It is the standard deviation of multiple historical maximum zonal wind speeds within the preset historical time period.

[0023] In an embodiment of the present application, the method also includes: obtaining the actual observation value of the target meteorological index of the target area and the circulation parameter prediction values ​​of the target area for multiple preset regional meteorological forecast models; determining the candidate prediction values ​​of the target meteorological index of the target area corresponding to each preset regional meteorological forecast model based on the circulation parameter prediction values ​​corresponding to each preset regional meteorological forecast model; determining the Pearson correlation coefficient between the actual observation value of the target meteorological index and each candidate prediction value of the target meteorological index; determining the preset regional meteorological forecast model corresponding to the candidate prediction value with the highest Pearson correlation coefficient as the target regional meteorological forecast model, so as to predict the target meteorological index according to the target regional meteorological forecast model.

[0024] A second aspect of an embodiment of the present application provides a device for predicting drought risk in a watershed, comprising:

[0025] A data acquisition module is used to obtain the current circulation parameters of the basin to be predicted, the historical forecast values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological index, wherein the target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream;

[0026] A current prediction value determination module is used to determine the current prediction value of the target meteorological index of the basin to be predicted based on the current circulation parameters;

[0027] A target dynamic weight determination module is used to determine the target dynamic weight corresponding to the target meteorological index based on a preset index dynamic weight determination model and according to the historical forecast value of the target meteorological index and the historical climate scenario label;

[0028] A drought index determination module is used to determine the drought index of the basin to be predicted based on the current predicted value of the target meteorological index and the target dynamic weight;

[0029] The target drought risk probability determination module is used to determine the target drought risk probability of the basin to be predicted based on the drought index.

[0030] In the embodiment of the present application, the target dynamic weight includes the weight of the eastward extension index of the South Asian high pressure, the weight of the westward extension index of the western Pacific subtropical high pressure, and the weight of the northward movement index of the East Asian subtropical westerly jet stream. The drought index determination module is further used to determine the drought index of the basin to be predicted according to the following formula:

[0031] EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|)

[0032] Among them, EDI is the drought index, α is the weight of the eastward extension index of the South Asian high pressure, SHI is the eastward extension index of the South Asian high pressure, β is the weight of the westward extension index of the western Pacific subtropical high pressure, WPI is the westward extension index of the western Pacific subtropical high pressure, JNI is the northward movement index of the East Asian subtropical westerly jet, and γ is the weight of the northward movement index of the East Asian subtropical westerly jet.

[0033] In an embodiment of the present application, the target drought risk probability determination module is also used to: determine the target drought index interval corresponding to the drought index; based on the correspondence between the predetermined drought index interval and the drought risk probability, determine the target drought risk probability of the basin to be predicted according to the target drought index interval.

[0034] In the embodiment of the present application, the current circulation parameters include the current longitude value of the eastern boundary of the South Asian High and the current geopotential height value of the South Asian High. The current prediction value determination module is further used to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula:

[0035]

[0036] Among them, SHI is the index of the eastward extension of the South Asian high pressure, λ east is the longitude value of the eastern boundary of the current South Asian high pressure, is the average of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, σ east is the standard deviation of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, Z 200hPa(i,j) It is the current South Asian high potential height value at each preset position on the preset pressure layer. It is the average value of the current South Asian high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

[0037] In the embodiment of the present application, the current circulation parameters include the current longitude value of the western boundary of the western Pacific subtropical high pressure and the current geopotential height value of the western Pacific subtropical high pressure. The current prediction value determination module is further used to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula:

[0038]

[0039] Wherein, WPI is the westward extension index of the western Pacific subtropical high pressure, λ west is the longitude of the western boundary of the current western Pacific subtropical high pressure, is the average of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, σ west is the standard deviation of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, Z 200hPa(i,j) is the current geopotential height value of the western Pacific subtropical high pressure at each preset location on the preset pressure layer, It is the average value of the current western Pacific subtropical high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of preset positions, the longitude value of the preset position ranges from m to n, and the latitude value of the preset position ranges from k to l.

[0040] In the embodiment of the present application, the current circulation parameters include the latitude value of the current maximum zonal wind speed axis and the current maximum zonal wind speed at the current moment. The current prediction value determination module is further used to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula:

[0041]

[0042] Among them, JNI is the index of the northward movement of the East Asian subtropical westerly jet stream, φ axis is the latitude of the axis of the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, σ axis is the standard deviation of the latitude values ​​of the historical maximum zonal wind speed axis within the preset historical time period, U max is the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speeds within the preset historical time period, σ max It is the standard deviation of multiple historical maximum zonal wind speeds within the preset historical time period.

[0043] In the embodiment of the present application, the device further includes a target area weather forecast mode, which is used to:

[0044] Obtaining actual observation values ​​of target meteorological indices in a target area and predicted values ​​of circulation parameters of the target area from meteorological forecast models in multiple preset areas;

[0045] Determining candidate prediction values ​​of target meteorological indices for target areas corresponding to the meteorological forecast models for the respective preset areas based on the predicted values ​​of circulation parameters corresponding to the meteorological forecast models for the respective preset areas;

[0046] Determine the Pearson correlation coefficient between the actual observed value of the target meteorological index and each candidate predicted value of the target meteorological index;

[0047] The preset regional weather forecast model corresponding to the candidate prediction value with the highest Pearson correlation coefficient is determined as the target regional weather forecast model, so as to predict the target weather index according to the target regional weather forecast model.

[0048] A third aspect of an embodiment of the present application provides an electronic device, comprising: a memory configured to store instructions; and a processor configured to call instructions from the memory and implement the above-mentioned method for basin drought risk prediction when executing the instructions.

[0049] A fourth aspect of an embodiment of the present application provides a machine-readable storage medium having stored thereon instructions for enabling a machine to execute the above-mentioned method for predicting drought risk in a watershed.

[0050] A fifth aspect of an embodiment of the present application provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements the above-mentioned method for predicting watershed drought risks.

[0051] The above technical solution, this application obtains the current circulation parameters of the basin to be predicted, the historical predicted values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological index so that the current predicted value of the target meteorological index of the basin to be predicted can be determined based on the current circulation parameters. The target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream. Determining the current predicted value of the target meteorological index makes it possible to subsequently calculate the drought index of the basin to be predicted based on the current predicted value of the target meteorological index. Therefore, this application takes into account the impact of the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream on the drought risk prediction of the basin to be predicted. Predicting the drought risk of the basin to be predicted based on the above three indices can improve the prediction accuracy of the drought risk. This application is also based on a preset index dynamic weight determination model. According to the historical prediction value of the target meteorological index and the historical climate scenario label, the target dynamic weight corresponding to the target meteorological index is determined. Based on the current prediction value of the target meteorological index and the target dynamic weight of the target meteorological index, the drought index of the basin to be predicted can be determined, and then the drought risk probability of the basin to be predicted can be determined based on the drought index, further improving the prediction accuracy of the basin drought risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0053] Figure 1 A schematic diagram of a flow chart of a method for predicting drought risk in a watershed according to an embodiment of the present application is shown;

[0054] Figure 2 The following schematically shows a structural block diagram of a device for predicting drought risk in a watershed according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. 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.

[0056] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0057] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0058] 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 for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0059] Figure 1 The flowchart for basin drought risk prediction in one embodiment of the present application is schematically shown. Figure 1 As shown, the embodiment of the present application provides a method for predicting drought risk in a watershed. Taking the method applied to a processor as an example, the method may include the following steps:

[0060] Step S101, obtain the current circulation parameters of the basin to be predicted, the historical forecast value of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario label corresponding to the target meteorological index, wherein the target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream.

[0061] Step S102: determining the current predicted value of the target meteorological index of the basin to be predicted based on the current circulation parameters.

[0062] Step S103 , based on a preset index dynamic weight determination model, the target dynamic weight corresponding to the target meteorological index is determined according to the historical forecast value of the target meteorological index and the historical climate scenario label.

[0063] Step S104: determining the drought index of the basin to be predicted based on the current predicted value of the target meteorological index and the target dynamic weight.

[0064] Step S105: determining the target drought risk probability of the watershed to be predicted based on the drought index.

[0065] It is understood that the basin to be predicted is a river area where drought risk needs to be predicted, such as the Yangtze River Basin or the Yellow River Basin. Current circulation parameters include the current longitude of the eastern boundary of the South Asian High, the current geopotential height of the South Asian High, the current longitude of the western boundary of the Western Pacific Subtropical High, the current geopotential height of the Western Pacific Subtropical High, the current latitude of the axis of maximum zonal wind speed, and the current maximum zonal wind speed. Historical forecast values ​​are historical forecast values ​​of the target meteorological index. Historical climate scenario labels refer to historical El Niño, La Niña, and climate scenarios between El Niño and La Niña. Current forecast values ​​refer to the current forecast values ​​of the target meteorological index. The South Asian High Eastward Extension Index refers to the eastward extension of the high pressure layer in southern Asia. The Western Pacific Subtropical High Westward Extension Index refers to the westward extension of the subtropical high pressure layer in the western Pacific. The East Asian Subtropical Westerly Jet Northward Movement Index refers to the northward movement of the westerly jet in the subtropical region of eastern Asia. The eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream all affect the drought index value. The preset index dynamic weight determination model determines the dynamic weight of a pre-set target meteorological index and can be a Transformer-LSTM hybrid model. The target dynamic weight refers to the weight of the target meteorological index at the time of prediction. The drought index represents the probability of drought risk. The target drought risk probability refers to the probability of drought at the time of prediction.

[0066] Specifically, the South Asian High Eastward Extension Index, the Western Pacific Subtropical High Westward Extension Index, and the East Asian Subtropical Westerly Jet Northward Extension Index are indices that affect the drought index. The processor predicts these three indices based on the current prediction value, and then predicts the drought index based on these three indices. This allows the subsequent processor to predict the drought risk probability based on the drought index. The three indices have different impacts on the drought index. Therefore, this application characterizes the impact of the three indices on the drought index based on the target dynamic weight, and then accurately predicts the drought index to improve the accuracy of drought probability prediction.

[0067] The above technical solution, this application obtains the current circulation parameters of the basin to be predicted, the historical predicted values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological index so that the current predicted value of the target meteorological index of the basin to be predicted can be determined based on the current circulation parameters. The target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream. Determining the current predicted value of the target meteorological index makes it possible to subsequently calculate the drought index of the basin to be predicted based on the current predicted value of the target meteorological index. Therefore, this application takes into account the impact of the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream on the drought risk prediction of the basin to be predicted. Predicting the drought risk of the basin to be predicted based on the above three indices can improve the prediction accuracy of the drought risk. This application is also based on a preset index dynamic weight determination model. According to the historical prediction value of the target meteorological index and the historical climate scenario label, the target dynamic weight corresponding to the target meteorological index is determined. Based on the current prediction value of the target meteorological index and the target dynamic weight of the target meteorological index, the drought index of the basin to be predicted can be determined, and then the drought risk probability of the basin to be predicted can be determined based on the drought index, further improving the prediction accuracy of the basin drought risk.

[0068] In one embodiment, the target dynamic weights include an index weight of the eastward extension of the South Asian high pressure, an index weight of the westward extension of the western Pacific subtropical high pressure, and an index weight of the northward movement of the East Asian subtropical westerly jet stream. The drought index of the basin to be predicted is determined based on current data of the target meteorological index and the target dynamic weights, including determination according to the following formula:

[0069] EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|)

[0070] Among them, EDI is the drought index, α is the weight of the eastward extension index of the South Asian high pressure, SHI is the eastward extension index of the South Asian high pressure, β is the weight of the westward extension index of the western Pacific subtropical high pressure, WPI is the westward extension index of the western Pacific subtropical high pressure, JNI is the northward movement index of the East Asian subtropical westerly jet, and γ is the weight of the northward movement index of the East Asian subtropical westerly jet.

[0071] It can be understood that the weight of the South Asian High Eastward Extension Index is the weight of the Eastward Extension Index of the High Pressure Layer in Southern Asia. The weight of the West Pacific Subtropical High Westward Extension Index is the weight of the West Pacific Subtropical High Pressure Layer Westward Extension Index. The weight of the East Asian Subtropical Westerly Jet Northward Movement Index is the weight of the East Asian Subtropical Westerly Jet Northward Movement Index. The South Asian High Eastward Extension Index refers to the index of the Eastward Extension of the High Pressure Layer in Southern Asia. The West Pacific Subtropical High Westward Extension Index refers to the index of the West Pacific Subtropical High Pressure Layer Westward Extension. The East Asian Subtropical Westerly Jet Northward Movement Index refers to the index of the Northward Movement of the Westerly Jet in the Subtropical Region of Eastern Asia. The South Asian High Eastward Extension Index, the West Pacific Subtropical High Westward Extension Index and the East Asian Subtropical Westerly Jet Northward Movement Index will all affect the value of the drought index. The drought index is an index that characterizes the probability of drought risk.

[0072] Specifically, the processor can calculate the drought index by combining the index of the eastward extension of the South Asian high pressure, the index of the westward extension of the western Pacific subtropical high pressure, the index of the northward movement of the East Asian subtropical westerly jet stream, the weight of the eastward extension index of the South Asian high pressure, the weight of the westward extension index of the western Pacific subtropical high pressure, and the weight of the northward movement index of the East Asian subtropical westerly jet stream. The specific calculation formula is as above.

[0073] In one embodiment, determining the drought risk probability of the basin to be predicted based on the drought index includes: determining a target drought index interval corresponding to the drought index; and determining the target drought risk probability of the basin to be predicted based on the target drought index interval based on the correspondence between the predetermined drought index interval and the drought risk probability.

[0074] It can be understood that the target drought index range is the range of drought index. The drought risk probability is the probability of drought risk occurring.

[0075] Specifically, the target drought risk probability can be determined based on the drought index range. For example, when the drought index is greater than 1.5, the drought probability is greater than 80%; when the drought index is greater than 1.0 and less than or equal to 1.5, the drought probability is greater than 50% and less than or equal to 80%; and when the drought index is greater than 0.5 and less than or equal to 1.0, the drought probability is less than or equal to 50%.

[0076] In one embodiment, the current circulation parameters include the current longitude value of the eastern boundary of the South Asian High and the current geopotential height value of the South Asian High. Determining the current data of the target meteorological index of the basin to be predicted based on the current circulation parameters includes determining according to the following formula:

[0077]

[0078] Among them, SHI is the index of the eastward extension of the South Asian high pressure, λ east is the longitude value of the eastern boundary of the current South Asian high pressure, is the average of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, σ east is the standard deviation of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, Z 200hPa(i,j) It is the current South Asian high potential height value at each preset position on the preset pressure layer. It is the average value of the current South Asian high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

[0079] It can be understood that the current longitude value of the eastern boundary of the South Asian High Pressure is the longitude value of the eastern boundary of the current high-pressure layer in southern Asia. The preset historical time period can be the past ten years. The historical longitude value of the eastern boundary of the South Asian High Pressure can be the longitude value of the eastern boundary of the high-pressure layer in southern Asia in the past ten years. The preset pressure layer can be an atmospheric layer under an atmospheric pressure of 200hPa. The preset position is a position with different pre-set longitude and latitude values ​​within the range of longitude values ​​from m to n and latitude values ​​from k to l. The current geopotential height value of the South Asian High Pressure is the geopotential height of the South Asian High Pressure corresponding to different longitude and latitude values ​​in the atmospheric layer under the current atmospheric pressure of 200hPa.

[0080] Specifically, the South Asian High Eastward Extension Index can be determined based on the current longitude of the eastern boundary of the South Asian High, the average of the historical longitudes of the eastern boundary of the South Asian High, the standard deviation of the historical longitudes of the eastern boundary of the South Asian High, the current geopotential height of the South Asian High, and the average of the current geopotential height of the South Asian High. The specific formula is as above.

[0081] In one embodiment, the current circulation parameters include the current longitude value of the western boundary of the western Pacific subtropical high pressure and the current geopotential height value of the western Pacific subtropical high pressure. According to the current circulation parameters, the current data of the target meteorological index of the basin to be predicted is determined, including determining according to the following formula:

[0082]

[0083] Wherein, WPI is the westward extension index of the western Pacific subtropical high pressure, λ west is the longitude of the western boundary of the current western Pacific subtropical high pressure, is the average of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, σ westis the standard deviation of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, Z 200hPa(i,j) is the current geopotential height value of the western Pacific subtropical high pressure at each preset location on the preset pressure layer, It is the average value of the current western Pacific subtropical high potential height values ​​of multiple preset locations on the preset pressure layer, i is the longitude value of the preset location, j is the latitude value of the preset location, N is the number of preset locations, the longitude value of the preset location ranges from a to b, and the latitude value of the preset location ranges from c to d.

[0084] It can be understood that the current longitude value of the western boundary of the western Pacific subtropical high pressure is the longitude value of the western boundary of the current high-pressure layer in the western Pacific subtropical region. The preset historical time period can be the past ten years. The historical longitude value of the western boundary of the western Pacific subtropical high pressure can be the longitude value of the western boundary of the high-pressure layer in the western Pacific subtropical region in the past ten years. The preset pressure layer can be the atmospheric layer under an atmospheric pressure of 200hPa. The preset position is a position with different pre-set longitude and latitude values ​​within the range of a to b for the longitude value and c to d for the latitude value. The current geopotential height value of the western Pacific subtropical high pressure is the geopotential height of the western Pacific subtropical high pressure corresponding to different longitude and latitude values ​​in the atmospheric layer under the current atmospheric pressure of 200hPa.

[0085] Specifically, the westward extension index of the western Pacific subtropical high pressure can be determined based on the current western Pacific subtropical high pressure western boundary longitude value, the average of the historical western Pacific subtropical high pressure western boundary longitude values, the standard deviation of the historical western Pacific subtropical high pressure western boundary longitude values, the current western Pacific subtropical high pressure geopotential height value and the average of the current western Pacific subtropical high pressure geopotential height values. The specific formula is as above.

[0086] In one embodiment, the current circulation parameters include the latitude value of the axis of the current maximum latitudinal wind speed and the current maximum latitudinal wind speed at the current moment. Determining the current data of the target meteorological index of the basin to be predicted based on the current circulation parameters includes determining according to the following formula:

[0087]

[0088] Among them, JNI is the index of the northward movement of the East Asian subtropical westerly jet stream, φ axis is the latitude of the axis of the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, σ axis is the standard deviation of the latitude values ​​of the historical maximum zonal wind speed axis within the preset historical time period, U max is the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speeds within the preset historical time period, σ max It is the standard deviation of multiple historical maximum zonal wind speeds within the preset historical time period.

[0089] It can be understood that the current maximum latitudinal wind speed axis latitude is the latitude corresponding to the axis where the current latitudinal wind speed reaches its maximum value. The historical maximum latitudinal wind speed axis latitude is the latitude corresponding to the axis where the historical latitudinal wind speed reaches its maximum value. The current maximum latitudinal wind speed is the current maximum wind speed in the east-west direction. The historical maximum latitudinal wind speed is the historical maximum wind speed in the east-west direction.

[0090] Specifically, the northward movement index of the East Asian subtropical westerly jet stream can be determined based on the latitude value of the current maximum zonal wind speed axis, the average value of the latitude value of the historical maximum zonal wind speed axis, the standard deviation of the latitude value of the historical maximum zonal wind speed axis, the current maximum zonal wind speed, the average value of the historical maximum zonal wind speed, and the standard deviation of the historical maximum zonal wind speed.

[0091] In one embodiment, the method also includes: obtaining the actual observation value of the target meteorological index of the target area and the circulation parameter prediction values ​​of the target area for multiple preset regional meteorological forecast models; determining the candidate prediction values ​​of the target meteorological index of the target area corresponding to each preset regional meteorological forecast model based on the circulation parameter prediction values ​​corresponding to each preset regional meteorological forecast model; determining the Pearson correlation coefficient between the actual observation value of the target meteorological index and each candidate prediction value of the target meteorological index; determining the preset regional meteorological forecast model corresponding to the candidate prediction value with the highest Pearson correlation coefficient as the target regional meteorological forecast model, so as to predict the target meteorological index according to the target regional meteorological forecast model.

[0092] It is understood that the target area corresponds to the actual observation value, which may or may not include the basin to be predicted. Target meteorological indices include the index of the eastward extension of the South Asian High, the index of the westward extension of the Western Pacific Subtropical High, and the index of the northward movement of the East Asian Subtropical Westerly Jet. The actual observation value can be ERA5 reanalysis data, where ERA5 is a high-resolution global reanalysis dataset produced by the European Centre for Medium-Range Weather Forecasts (ECMWF). The preset regional meteorological forecast model can be a sub-seasonal-to-seasonal (S2S) numerical model such as the US CFSv2 (CFS), China's BCC-CSM2, and Europe's ECMWF (EC). The circulation parameter prediction values ​​are the circulation parameters predicted by sub-seasonal-to-seasonal (S2S) numerical models such as the US CFSv2 (CFS), China's BCC-CSM2, and Europe's ECMWF (EC). Candidate prediction values ​​are the prediction values ​​of different target meteorological indices determined based on the predicted circulation parameter values. The target regional meteorological forecast model is the candidate prediction value with the highest Pearson correlation coefficient to predict the target meteorological index.

[0093] Specifically, circulation parameter predictions are made based on sub-seasonal-to-seasonal (S2S) numerical models, such as the US CFSv2 (CFS), China's BCC-CSM2, and Europe's ECMWF (EC), to obtain candidate predictions for different pre-set regional weather forecast models. The candidate predictions are screened based on the Pearson correlation coefficient, and the pre-set regional weather forecast model corresponding to the candidate prediction value with the highest Pearson correlation coefficient is selected as the target regional weather forecast model, and the target weather index is then predicted. For example, circulation parameter predictions required to calculate the South Asian High Eastward Extension Index are made based on sub-seasonal-to-seasonal (S2S) numerical models, such as the US CFSv2 (CFS), China's BCC-CSM2, and Europe's ECMWF (EC), to obtain multiple South Asian High Eastward Extension Indexes for different pre-set regional weather forecast models. The multiple South Asian High Eastward Extension Indexes are screened based on the Pearson correlation coefficient, and the pre-set regional weather forecast model corresponding to the South Asian High Eastward Extension Index with the highest Pearson correlation coefficient is selected as the target regional weather forecast model, and the South Asian High Eastward Extension Index is then predicted. The method for determining the target area meteorological forecast model corresponding to the westward extension index of the western Pacific subtropical high pressure and the northward movement index of the East Asian subtropical westerly jet is as above.

[0094] The specific steps can be as follows:

[0095] In order to address the shortcomings of existing technologies in predicting extreme drought events in the summer and autumn in the Yangtze River Basin, this paper provides an extreme drought prediction method based on the multi-factor synergistic mechanism of the South Asian High Eastward Extension Index (SHI), the Western Pacific Subtropical High (referred to as the Subtropical High) Westward Extension Index (WPI) and the East Asian Subtropical Westerly Jet (referred to as the Westerly Jet) Northward Movement Index (JNI). By constructing a SHI-WPI-JNI coupled prediction model, a quantitative early warning system for extreme drought is established, which significantly improves the prediction accuracy of extreme drought events in the Yangtze River Basin.

[0096] (1) Calculation of key circulation indices

[0097] European Center for Meteorological Reanalysis Data (ERA5) from 1980 to 2022 are collected, including parameters such as 200hPa, 500hPa, and 850hPa geopotential heights and zonal wind speeds.

[0098] (a) Calculation of the South Asian High Eastward Extension Index (SHI)

[0099] Based on the 200hPa geopotential height grid data from 1980 to 2022, the average climatological state of the easternmost position of the 200hPa South Asian High (50°E-180°, 10°N-60°N ≥ 12360gpm contour area) in summer and autumn (July-October) is first calculated. and standard deviation (σeast ), and the climatological mean of the potential height at each grid point in the main area Next, the standardized offset of the longitude of the eastern boundary of the South Asian High relative to the climatological position is calculated. The anomaly intensity of the geopotential height relative to the climatological average is then simultaneously calculated. Finally, the longitude offset is multiplied and coupled with the geopotential height anomaly to reflect the synergistic effect of the "eastward extension + dynamic enhancement" of the South Asian High. The specific formula is as follows:

[0100]

[0101] Based on the ERA5 data, the South Asian High Pressure Eastward Extension Index (SHI) in the summer and autumn of 2022 is 3.2.

[0102] (b) Calculation of the Westward Extension Index (WPI) of the Subtropical High

[0103] Based on the 500hPa geopotential height grid data from 1980 to 2022, the climatological average of the longitude at the westernmost position of the subtropical high (70°E-180°, 10°N-60°N ≥ 5880gpm contour area) in summer and autumn (July-October) is first calculated. and standard deviation (σ west ), and the climatological mean of the potential height at each grid point in the main area Next, the westward extension distance of the subtropical high's westward extension ridge point relative to the climatological position is calculated. The anomaly intensity of the geopotential height in the main region relative to the climatological mean is then simultaneously calculated. Finally, the westward extension distance is multiplied and coupled with the geopotential height anomaly to reflect the combined contribution of "westward extension range + system intensity." The specific formula is as follows:

[0104]

[0105] Based on the ERA5 data, the westward extension index (WPI) of the subtropical high in the summer and autumn of 2022 is 4.1.

[0106] (c) Calculation of the Jet Stream Northward Index (JNI)

[0107] Based on the 200hPa zonal wind speed grid data from 1980 to 2022, the climatological average of the maximum zonal wind speed (axis) at the latitude of the 200hPa jet stream area (60°E-150°E, 10°N-60°N ≥ 30m / s) in summer and autumn (July-October) is first calculated. and standard deviation (σ axis ), and the climatological mean of the maximum zonal wind speed in the jet stream region and standard deviation (σ max); then calculate the standardized northward displacement of the jet stream axis's latitude relative to the climatological state; then simultaneously calculate the anomaly intensity of the maximum wind speed in the jet stream area relative to the climatological mean; finally, multiply the latitude offset by the wind speed enhancement to represent the positive feedback mechanism of "northward displacement + dynamic enhancement". The specific formula is as follows:

[0108]

[0109] Based on ERA5 data, the northward movement index (JNI) of the westerly jet stream in the summer and autumn of 2022 is 2.5.

[0110] (2) Construction of a multi-factor synergistic extreme drought prediction model

[0111] Based on the above-obtained South Asian High Eastward Extension Index (SHI), Subtropical High Westward Extension Index (WPI), and Westerly Jet Stream Northward Extension Index (JNI), a statistical prediction model for the Extreme Drought Index (EDI) was constructed. Dynamic weight parameters α, β, and γ were introduced. The product term characterizes the synergistic effect between factors, the exponential term captures the nonlinear mutation characteristics, and the dynamic weight allocation mechanism improves the model's adaptability to climate scenarios. The specific formula is as follows.

[0112] EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|) (4)

[0113] (3) Dynamic weight intelligent allocation

[0114] This extreme drought prediction model, based on multiple factors including the South Asian High Eastward Extension Index (SHI), the West Pacific Subtropical High Westward Extension Intensity Index (WPI), and the Northward Movement Index (JNI), employs a Transformer-LSTM hybrid model, combining the Transformer's long-term feature extraction with the LSTM's short-term memory. The input layer embeds climate scenario labels (El Niño / La Niña / neutral) and historical circulation factor time series data, while the output layer generates dynamic weights α, β, and γ. During the pre-training phase, historical drought events are used as labels. An attention mechanism is used to learn the spatiotemporal dependencies between the contributions of these factors under different climate scenarios, dynamically optimizing the weights of each factor.

[0115] (4) Multi-model forecast skill evaluation

[0116] This study evaluated the forecasting skills of the South Asian High Eastward Index (SHI), the Subtropical High Westward Index (WPI), and the Jet Stream Northward Index (JNI) for subseasonal-seasonal (S2S) numerical models, including the US CFSv2 (CFS), China BCC-CSM2, and Europe ECMWF (EC), to provide high-precision input for extreme drought prediction. Specifically, the following methods were used:

[0117] We obtained model return data from 2000 to 2020, extracted forecasts for SHI, WPI, and JNI, and simultaneously collected ERA5 reanalysis data for the corresponding periods as true observations. For each circulation factor n (n = SHI, WPI, JNI) for each model m, we calculated the trend fit (TS), which is the Pearson correlation coefficient between the forecast (F) and the observation (O). This measures the consistency of circulation trends, using the formula shown below.

[0118]

[0119] Set threshold TS m,n >0.6, find the optimized model-factor combination (such as the EC model's forecast of WPI).

[0120] (5) Generation of extreme drought warning results

[0121] The optimized multi-model circulation factor forecast sequence was input into the weight allocation model in step 3, resulting in α, β, and γ weights of 0.30, 0.45, and 0.25, respectively. Substituting these into equations (1)-(3), the model predicted SHI, WPI, and JNI to be 2.8, 3.9, and 3.1, respectively. This yielded an EDI of 6.4 for the summer and autumn of 2022 (Equation 4), indicating an extreme drought probability >80% in the Yangtze River Basin. The ERA5 back-calculated values ​​and model predictions are shown in the table below.

[0122] Table 1 Drought index prediction table

[0123]

[0124] Figure 2 The following schematically shows a block diagram of a device for predicting drought risk in a watershed according to an embodiment of the present application. Figure 2 As shown, an embodiment of the present application provides a device 200 for predicting drought risk in a watershed, and the device 200 may include:

[0125] The data acquisition module 210 is used to obtain the current circulation parameters of the basin to be predicted, the historical prediction values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological index, wherein the target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream.

[0126] The current prediction value determination module 220 is used to determine the current prediction value of the target meteorological index of the basin to be predicted based on the current circulation parameters.

[0127] The target dynamic weight determination module 230 is used to determine the target dynamic weight corresponding to the target meteorological index based on a preset index dynamic weight determination model and according to the historical forecast value and historical climate scenario label of the target meteorological index.

[0128] The drought index determination module 240 is used to determine the drought index of the basin to be predicted based on the current predicted value of the target meteorological index and the target dynamic weight.

[0129] The target drought risk probability determination module 250 is used to determine the target drought risk probability of the basin to be predicted based on the drought index.

[0130] The above technical solution, this application obtains the current circulation parameters of the basin to be predicted, the historical predicted values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological index so that the current predicted value of the target meteorological index of the basin to be predicted can be determined based on the current circulation parameters. The target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream. Determining the current predicted value of the target meteorological index makes it possible to subsequently calculate the drought index of the basin to be predicted based on the current predicted value of the target meteorological index. Therefore, this application takes into account the impact of the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream on the drought risk prediction of the basin to be predicted. Predicting the drought risk of the basin to be predicted based on the above three indices can improve the prediction accuracy of the drought risk. This application is also based on a preset index dynamic weight determination model. According to the historical prediction value of the target meteorological index and the historical climate scenario label, the target dynamic weight corresponding to the target meteorological index is determined. Based on the current prediction value of the target meteorological index and the target dynamic weight of the target meteorological index, the drought index of the basin to be predicted can be determined, and then the drought risk probability of the basin to be predicted can be determined based on the drought index, further improving the prediction accuracy of the basin drought risk.

[0131] In one embodiment, the target dynamic weights include the weight of the eastward extension index of the South Asian high pressure, the weight of the westward extension index of the western Pacific subtropical high pressure, and the weight of the northward movement index of the East Asian subtropical westerly jet stream. The drought index determination module is further configured to determine the drought index of the basin to be predicted according to the following formula:

[0132] EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|)

[0133] Among them, EDI is the drought index, α is the weight of the eastward extension index of the South Asian high pressure, SHI is the eastward extension index of the South Asian high pressure, β is the weight of the westward extension index of the western Pacific subtropical high pressure, WPI is the westward extension index of the western Pacific subtropical high pressure, JNI is the northward movement index of the East Asian subtropical westerly jet, and γ is the weight of the northward movement index of the East Asian subtropical westerly jet.

[0134] In one embodiment, the target drought risk probability determination module 250 is further used to: determine a target drought index interval corresponding to the drought index; and determine the target drought risk probability of the basin to be predicted according to the target drought index interval based on the correspondence between the predetermined drought index interval and the drought risk probability.

[0135] In one embodiment, the current circulation parameters include the current longitude value of the eastern boundary of the South Asian High and the current geopotential height value of the South Asian High. The current prediction value determination module 220 is further configured to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula:

[0136]

[0137] Among them, SHI is the index of the eastward extension of the South Asian high pressure, λ east is the longitude value of the eastern boundary of the current South Asian high pressure, is the average of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, σ east is the standard deviation of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, Z 200hPa(i,j) It is the current South Asian high potential height value at each preset position on the preset pressure layer. It is the average value of the current South Asian high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

[0138] In one embodiment, the current circulation parameters include the current longitude value of the western boundary of the western Pacific subtropical high pressure and the current geopotential height value of the western Pacific subtropical high pressure. The current prediction value determination module 220 is further configured to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula:

[0139]

[0140] Wherein, WPI is the westward extension index of the western Pacific subtropical high pressure, λ west is the longitude of the western boundary of the current western Pacific subtropical high pressure, is the average of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, σ westis the standard deviation of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, Z 200hPa(i,j) is the current geopotential height value of the western Pacific subtropical high pressure at each preset location on the preset pressure layer, It is the average value of the current western Pacific subtropical high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of preset positions, the longitude value of the preset position ranges from m to n, and the latitude value of the preset position ranges from k to l.

[0141] In one embodiment, the current circulation parameters include the latitude value of the current maximum zonal wind speed axis and the current maximum zonal wind speed at the current moment. The current prediction value determination module is further configured to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula:

[0142]

[0143] Among them, JNI is the index of the northward movement of the East Asian subtropical westerly jet stream, φ axis is the latitude of the axis of the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, σ axis is the standard deviation of the latitude values ​​of the historical maximum zonal wind speed axis within the preset historical time period, U max is the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speeds within the preset historical time period, σ max It is the standard deviation of multiple historical maximum zonal wind speeds within the preset historical time period.

[0144] In one embodiment, the device also includes a target area weather forecast model, which is used to: obtain the actual observation value of the target weather index of the target area and the circulation parameter prediction values ​​of the target area of ​​multiple preset area weather forecast models; determine the candidate prediction values ​​of the target weather index of the target area corresponding to each preset area weather forecast model based on the circulation parameter prediction values ​​corresponding to each preset area weather forecast model; determine the Pearson correlation coefficient between the actual observation value of the target weather index and each candidate prediction value of the target weather index; determine the preset area weather forecast model corresponding to the candidate prediction value with the highest Pearson correlation coefficient as the target area weather forecast model, so as to predict the target weather index according to the target area weather forecast model.

[0145] An embodiment of the present application provides an electronic device, comprising: a memory configured to store instructions; and a processor configured to call instructions from the memory and implement the above-mentioned method for predicting watershed drought risks when executing the instructions.

[0146] An embodiment of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for predicting watershed drought risk.

[0147] An embodiment of the present application provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements the above-mentioned method for predicting watershed drought risk.

[0148] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0149] The above are merely 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 modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for predicting drought risk in a watershed, characterized in that: The method comprises: Obtain the current circulation parameters of the basin to be predicted, the historical forecast values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological indexes, wherein the target meteorological indexes include the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream; Determining a current forecast value of a target meteorological index of the basin to be forecasted based on the current circulation parameter; Based on a preset index dynamic weight determination model, determining a target dynamic weight corresponding to the target meteorological index according to a historical forecast value of the target meteorological index and the historical climate scenario label; Determining the drought index of the basin to be predicted according to the current predicted value of the target meteorological index and the target dynamic weight; The target drought risk probability of the watershed to be predicted is determined according to the drought index.

2. The method according to claim 1, characterized in that The target dynamic weight includes an index weight of the eastward extension of the South Asian high pressure, an index weight of the westward extension of the western Pacific subtropical high pressure, and an index weight of the northward movement of the East Asian subtropical westerly jet stream. Determining the drought index of the basin to be predicted based on current data of the target meteorological index and the target dynamic weight includes determining according to the following formula: EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|) Among them, EDI is the drought index, α is the weight of the eastward extension index of the South Asian high pressure, SHI is the eastward extension index of the South Asian high pressure, β is the weight of the westward extension index of the western Pacific subtropical high pressure, WPI is the westward extension index of the western Pacific subtropical high pressure, JNI is the northward movement index of the East Asian subtropical westerly jet stream, and γ is the weight of the northward movement index of the East Asian subtropical westerly jet stream.

3. The method according to claim 1, characterized in that Determining the drought risk probability of the to-be-predicted basin according to the drought index includes: determining a target drought index range corresponding to the drought index; Based on the correspondence between the predetermined drought index interval and the drought risk probability, the target drought risk probability of the watershed to be predicted is determined according to the target drought index interval.

4. The method according to claim 1, wherein The current circulation parameters include the current longitude value of the eastern boundary of the South Asian High and the current geopotential height value of the South Asian High. Determining the current predicted value of the target meteorological index of the basin to be predicted based on the current circulation parameters includes determining according to the following formula: Among them, SHI is the index of the eastward extension of the South Asian high pressure, λ east is the longitude value of the eastern boundary of the current South Asian high pressure, is the average of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, σ east is the standard deviation of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, Z 200hPa(i,j) is the current South Asian high potential height value at each preset position on the preset pressure layer, It is the average value of the current South Asian high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of the preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

5. The method according to claim 1, characterized in that The current circulation parameters include the current longitude value of the western boundary of the western Pacific subtropical high pressure and the current geopotential height value of the western Pacific subtropical high pressure. Determining the current predicted value of the target meteorological index of the basin to be predicted based on the current circulation parameters includes determining according to the following formula: Wherein, WPI is the westward extension index of the western Pacific subtropical high pressure, λ west is the longitude of the western boundary of the current western Pacific subtropical high pressure, is the average of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, σ west is the standard deviation of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, Z 200hPa(i,j) is the current western Pacific subtropical high potential height value at each preset position on the preset pressure layer, It is the average value of the current western Pacific subtropical high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of the preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

6. The method according to claim 1, characterized in that The current circulation parameters include the latitude value of the current maximum latitudinal wind speed axis at the current moment and the current maximum latitudinal wind speed at the current moment. Determining the current predicted value of the target meteorological index of the basin to be predicted based on the current circulation parameters includes determining according to the following formula: Wherein, JNI is the northward movement index of the East Asian subtropical westerly jet stream, φ axis is the latitude value of the axis of the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, σ axis is the standard deviation of the multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, U max is the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speeds within the preset historical time period, σ max It is the standard deviation of multiple historical maximum zonal wind speeds within a preset historical time period.

7. The method according to claim 1, characterized in that The method further comprises: Obtaining actual observation values ​​of the target meteorological index of the target area and predicted values ​​of circulation parameters of the target area from multiple preset regional meteorological forecast models; Determining candidate prediction values ​​of the target meteorological index of the target area corresponding to each of the preset regional meteorological forecast modes according to the circulation parameter prediction values ​​corresponding to each of the preset regional meteorological forecast modes; Determining a Pearson correlation coefficient between the actual observed value of the target meteorological index and each of the candidate predicted values ​​of the target meteorological index; The preset regional weather forecast mode corresponding to the candidate prediction value with the highest Pearson correlation coefficient is determined as the target regional weather forecast mode, so as to predict the target weather index according to the target regional weather forecast mode.

8. A device for predicting drought risk in a watershed, characterized in that: include: A data acquisition module is used to obtain the current circulation parameters of the basin to be predicted, the historical forecast values ​​of the target meteorological index of the basin to be predicted in the past preset time period, and the historical climate scenario labels corresponding to the target meteorological index, wherein the target meteorological index includes the eastward extension index of the South Asian high pressure, the westward extension index of the western Pacific subtropical high pressure, and the northward movement index of the East Asian subtropical westerly jet stream; a current prediction value determination module, configured to determine a current prediction value of a target meteorological index of the basin to be predicted based on the current circulation parameters; A target dynamic weight determination module is configured to determine the target dynamic weight corresponding to the target meteorological index based on a preset index dynamic weight determination model and according to the historical forecast value of the target meteorological index and the historical climate scenario label; A drought index determination module, configured to determine the drought index of the basin to be predicted based on the current predicted value of the target meteorological index and the target dynamic weight; The target drought risk probability determination module is used to determine the target drought risk probability of the basin to be predicted based on the drought index.

9. The device according to claim 8, characterized in that The target dynamic weights include the weight of the eastward extension index of the South Asian high pressure, the weight of the westward extension index of the western Pacific subtropical high pressure, and the weight of the northward movement index of the East Asian subtropical westerly jet stream. The drought index determination module is further used to determine the drought index of the basin to be predicted according to the following formula: EDI=α*SHI+β*WPI*JNI+γ*exp(-|SHI-WPI|) Among them, EDI is the drought index, α is the weight of the eastward extension index of the South Asian high pressure, SHI is the eastward extension index of the South Asian high pressure, β is the weight of the westward extension index of the western Pacific subtropical high pressure, WPI is the westward extension index of the western Pacific subtropical high pressure, JNI is the northward movement index of the East Asian subtropical westerly jet stream, and γ is the weight of the northward movement index of the East Asian subtropical westerly jet stream.

10. The device according to claim 8, characterized in that The target drought risk probability determination module is further configured to: determining a target drought index range corresponding to the drought index; Based on the correspondence between the predetermined drought index interval and the drought risk probability, the target drought risk probability of the watershed to be predicted is determined according to the target drought index interval.

11. The device according to claim 8, characterized in that The current circulation parameters include the current longitude value of the eastern boundary of the South Asian High and the current geopotential height value of the South Asian High. The current prediction value determination module is further used to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula: Among them, SHI is the index of the eastward extension of the South Asian high pressure, λ east is the longitude value of the eastern boundary of the current South Asian high pressure, is the average of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, σ east is the standard deviation of the longitude values ​​of the eastern boundary of the South Asian High within the preset historical time period, Z 200hPa(i,j) is the current South Asian high potential height value at each preset position on the preset pressure layer, It is the average value of the current South Asian high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of the preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

12. The device according to claim 8, characterized in that The current circulation parameters include the current longitude value of the western boundary of the western Pacific subtropical high pressure and the current geopotential height value of the western Pacific subtropical high pressure. The current prediction value determination module is further used to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula: Wherein, WPI is the westward extension index of the western Pacific subtropical high pressure, λ west is the longitude of the western boundary of the current western Pacific subtropical high pressure, is the average of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, σ west is the standard deviation of the longitude values ​​of the western boundary of the western Pacific subtropical high pressure in the preset historical time period, Z 200hPa(i,j) is the current western Pacific subtropical high potential height value at each preset position on the preset pressure layer, It is the average value of the current western Pacific subtropical high potential height values ​​of multiple preset positions on the preset pressure layer, i is the longitude value of the preset position, j is the latitude value of the preset position, N is the number of the preset positions, the numerical range of the longitude value of the preset position is m to n, and the numerical range of the latitude value of the preset position is k to l.

13. The device according to claim 8, characterized in that The current circulation parameters include the current maximum zonal wind speed axis latitude value and the current maximum zonal wind speed at the current moment. The current prediction value determination module is further configured to determine the current prediction value of the target meteorological index of the basin to be predicted according to the following formula: Wherein, JNI is the northward movement index of the East Asian subtropical westerly jet stream, φ axis is the latitude value of the axis of the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, σ axis is the standard deviation of the multiple historical maximum zonal wind speed axis latitude values ​​within the preset historical time period, U max is the current maximum zonal wind speed, is the average value of multiple historical maximum zonal wind speeds within the preset historical time period, σ max It is the standard deviation of multiple historical maximum zonal wind speeds within a preset historical time period.

14. The device according to claim 8, characterized in that The device further includes a target area weather forecast model, wherein the target area weather forecast model is used to: Obtaining actual observation values ​​of the target meteorological index of the target area and predicted values ​​of circulation parameters of the target area from multiple preset regional meteorological forecast models; Determining candidate prediction values ​​of the target meteorological index of the target area corresponding to each of the preset regional meteorological forecast modes according to the circulation parameter prediction values ​​corresponding to each of the preset regional meteorological forecast modes; Determining a Pearson correlation coefficient between the actual observed value of the target meteorological index and each of the candidate predicted values ​​of the target meteorological index; The preset regional weather forecast mode corresponding to the candidate prediction value with the highest Pearson correlation coefficient is determined as the target regional weather forecast mode, so as to predict the target weather index according to the target regional weather forecast mode.

15. An electronic device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the method for watershed drought risk prediction according to any one of claims 1 to 7 when executing the instructions.

16. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for causing a machine to execute the method for predicting watershed drought risk according to any one of claims 1 to 7.

17. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for watershed drought risk prediction according to any one of claims 1 to 7.

Images