Reservoir daily runoff historical series calculation method and system fused with machine learning correction

Abstract

The invention discloses a reservoir daily runoff historical series calculation method and system fused with machine learning correction, and the method comprises the steps: S100: carrying out the calculation of a reservoir daily runoff historical series according to the short-series actually-measured runoff data of a target reservoir station and the long-series actually-measured runoff data of a reference station; estimating the runoff data of the target reservoir station in the historical long series of days by adopting a runoff correlation method and a hydrological comparison method respectively; s200, correcting the estimated historical long-series ten-day runoff data by adopting a machine learning model to obtain corrected historical long-series ten-day runoff data of the target reservoir station; and S300, performing time downscaling on the corrected historical long-series ten-day runoff data to obtain long-series daily runoff data of the target reservoir station. Under the condition that the actually measured runoff data of the reservoir basin is insufficient, the method can be used for calculating the historical long-series daily runoff data of the target reservoir, the calculation precision and the time resolution are remarkably improved, and the calculated runoff series results are checked to be reasonable.

Description

Technical Field

[0001] The present application belongs to the technical field of reservoir runoff estimation, and specifically relates to a method and system for estimating a historical series of reservoir daily runoff integrating machine learning correction. Background Art

[0002] The design runoff series (usually required to be more than 30 years) is an important basis for determining the scale of reservoirs, operating water levels and compiling reservoir dispatching regulations. However, many newly built reservoirs lack measured runoff data of sufficient years. It is usually necessary to first select similar basins upstream and downstream of the reservoir or in adjacent basins, and take hydrological stations with long series of measured runoff data in similar basins as reference stations, and use methods such as runoff correlation method and hydrological analogy method to calculate the design runoff series of the reservoir. The above method for calculating the design runoff series of reservoirs is recorded in the "Hydrological Calculation Specifications for Water Conservancy and Hydropower Engineering" No. SL / T-278.

[0003] The technical idea of ​​the runoff correlation method is to establish a statistical correlation between the short series of measured runoff at the reservoir station and the short series of measured runoff at the reference station during the same period, and to combine the statistical correlation and the long series of measured runoff data at the reference station to estimate the long series of runoff data at the reservoir station over the ten-day scale. The technical idea of ​​the hydrological analogy method is to establish a proportional relationship between the reservoir station and the reference station in terms of catchment area and surface rainfall, and based on this proportional relationship, estimate the long series of runoff data at the reservoir station over the ten-day scale using the long series of measured runoff data at the reference station.

[0004] However, the runoff correlation method and the hydrological analogy method do not consider the complexity of the basin runoff generation and convergence process. Both methods assume that the rainfall-runoff similarity of the reservoir basin (referring to the basin where the reservoir is located) and the reference basin (referring to the basin where the reference station is located) conform to a linear relationship, which deviates from the nonlinear characteristics of the actual runoff generation and convergence process, and may make it difficult for the calculated reservoir long-series runoff results to achieve high accuracy. In addition, the reservoir basin and the reference basin generally only basically meet the rainfall-runoff similarity on a longer time scale of more than ten days, which also makes it difficult for the time resolution of the calculated reservoir long-series runoff results to be refined to the day. As the reservoir operation becomes increasingly refined, the requirements for the accuracy and time resolution of the design runoff series results are also increasing. The reservoir design runoff series results calculated by the runoff correlation method, hydrological analogy method and other methods are difficult to support the refined operation of the reservoir. Summary of the invention

[0005] The purpose of this application is to provide a method and system for estimating the historical series of daily runoff of a reservoir integrated with machine learning correction. The method and system of this application can significantly improve the estimation accuracy and time resolution of long-series reservoir runoff data. The estimated long-series reservoir runoff data can meet the refined scheduling and operation of the reservoir.

[0006] To achieve the above objectives, on the one hand, the present application provides a method for estimating the historical series of daily runoff of a reservoir by integrating machine learning correction, including:

[0007] S100: Based on the short series measured runoff data of the target reservoir station and the long series measured runoff data of the reference station, the historical long series ten-day runoff data of the target reservoir station are estimated by using the runoff correlation method and the hydrological analogy method, which are recorded as the first long series estimated ten-day runoff data and the second long series estimated ten-day runoff data respectively;

[0008] S200: Use the machine learning model to correct the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data to obtain the corrected historical long series of ten-day runoff data for the target reservoir station;

[0009] The machine learning model is first trained using training samples, wherein the training samples include a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data for the same period; the machine learning model is trained using the short series of measured ten-day runoff data of the target reservoir station as output and the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data for the same period as input;

[0010] S300: Time downscaling the corrected historical long series of ten-day runoff data to obtain the long series of daily runoff data of the target reservoir station.

[0011] In some specific implementations, the machine learning model is first trained using training samples, further comprising:

[0012] S210: constructing a sample data set, wherein the sample data set includes a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data of the same period; dividing the sample data set into a training sample set and a test sample set;

[0013] S220: training the machine learning model using the training sample set;

[0014] S230: Using a test sample set to test the trained machine learning model;

[0015] Select a variety of different machine learning models for training and testing respectively, and use the machine learning model with the highest accuracy for calibration.

[0016] The above machine learning model may be one or more of a support vector machine model, a random forest model, a gradient boosting regression tree model, and a long short-term memory network model.

[0017] In some specific implementations, step S200 further includes:

[0018] The corrected historical long series of ten-day runoff data are corrected according to the relative deviation of water volume:

[0019]

[0020] Among them, Q' ml,旬 represents the corrected historical long-series ten-day runoff data; n represents the ten-day number of the short-series measured runoff data of the target reservoir station; Indicates the short series of measured ten-day runoff at the target reservoir station the sum of represents the measured ten-day runoff in the i-th short series; It indicates that the corrected historical long series of ten-day runoff The sum of runoff during the same period.

[0021] In some specific implementations, step S300 further includes:

[0022] The following are performed on the runoff of each decade in the corrected historical long series of runoff data:

[0023] Determine whether there is rainfall in the current ten-day period. If there is no rainfall, the current ten-day runoff is underground runoff. If there is rainfall, the current ten-day runoff is divided into underground runoff and surface runoff in proportion according to the rainfall in the current ten-day period.

[0024] For underground runoff, the daily underground runoff is obtained by time downscaling based on the equal runoff volume every day within ten days;

[0025] For surface runoff, Perform time downscaling to obtain daily surface runoff Among them, n represents the total number of days in the current decade, represents the surface runoff in the current decade, P 目标,i represents the rainfall in the reservoir basin on the i-th day of the current ten-day period, It indicates the total rainfall in the reservoir basin in the current decade;

[0026] For the current decade without rainfall, the daily groundrunoff is the daily runoff data; for the current decade with rainfall, the daily groundrunoff and daily surface runoff on the same day are added to obtain the daily runoff data.

[0027] On the other hand, the present application also provides a reservoir daily runoff history series estimation system integrating machine learning correction, including:

[0028] The first module is used to estimate the historical long-series ten-day runoff data of the target reservoir station based on the short-series measured runoff data of the target reservoir station and the long-series measured runoff data of the reference station, respectively using the runoff correlation method and the hydrological analogy method, which are recorded as the first long-series estimated ten-day runoff data and the second long-series estimated ten-day runoff data;

[0029] The second module is used to use the machine learning model to correct the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data to obtain the corrected historical long series of ten-day runoff data for the target reservoir station;

[0030] The machine learning model is first trained using training samples, wherein the training samples include a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data for the same period; the machine learning model is trained using the short series of measured ten-day runoff data of the target reservoir station as output and the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data for the same period as input;

[0031] The third module is used to time downscale the corrected historical long series of ten-day runoff data to obtain the long series of daily runoff data of the target reservoir station.

[0032] In some specific implementations, the second module further includes a correction submodule, which is used to correct the corrected historical long series of ten-day runoff data according to the relative deviation of water volume:

[0033]

[0034] Among them, Q' ml,旬 represents the corrected historical long-series ten-day runoff data; n represents the ten-day number of the short-series measured runoff data of the target reservoir station; Indicates the short series of measured ten-day runoff at the target reservoir station the sum of represents the measured ten-day runoff in the i-th short series; It indicates that the corrected historical long series of ten-day runoff The sum of runoff during the same period.

[0035] In some specific embodiments, the third module further includes:

[0036] Submodule 1 is used to determine whether there is rainfall in the current ten-day period. If there is no rainfall, the current ten-day runoff is underground runoff. If there is rainfall, the current ten-day runoff is divided into underground runoff and surface runoff in proportion according to the rainfall in the current ten-day period.

[0037] Submodule 2 is used to downscale the underground runoff to obtain the daily underground runoff according to the equal runoff volume every day within ten days;

[0038] Submodule 3 is used to analyze surface runoff according to Perform time downscaling to obtain daily surface runoff Among them, n represents the total number of days in the current decade, represents the surface runoff in the current decade, P 目标,irepresents the rainfall in the reservoir basin on the i-th day of the current ten-day period, It indicates the total rainfall in the reservoir basin in the current decade;

[0039] Submodule 4 is used to obtain the daily underground runoff data for the current decade without rainfall; for the current decade with rainfall, the daily underground runoff and the daily surface runoff on the same day are added to obtain the daily runoff data.

[0040] Compared with the prior art, this application has the following advantages and beneficial effects:

[0041] When the measured runoff data in the reservoir basin is insufficient, the present invention can be used to infer the long series of daily runoff data of the target reservoir, with the time resolution refined to the day. The calculation accuracy and time resolution are significantly improved, and the calculated runoff series results are verified to be reasonable. The calculated long series of reservoir runoff data can support the refined scheduling and operation of the reservoir. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the process of this application method;

[0043] Figure 2 The comparison between the measured ten-day runoff data and the estimated ten-day runoff data of the target reservoir station in the embodiment;

[0044] Figure 3 The comparison between the measured ten-day runoff data and the corrected ten-day runoff data of the target reservoir station during the training period in the embodiment;

[0045] Figure 4 The comparison between the measured ten-day runoff data and the corrected ten-day runoff data of the target reservoir station during the inspection period in the embodiment;

[0046] Figure 5 The comparison between the estimated long series daily runoff data and the short series measured daily runoff data of the target reservoir station in the embodiment;

[0047] Figure 6 It is the variation trend curve of the annual average runoff and annual rainfall in the reservoir basin in the embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application clearer, the specific implementation methods of this application will be described clearly and completely in conjunction with the accompanying drawings. Obviously, the specific implementation methods described are only part of the specific implementation methods of this application, not all of the specific implementation methods. Based on the specific implementation methods in this application, all other specific implementation methods obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The technical idea of ​​this application's method for estimating reservoir daily runoff history series by integrating machine learning correction is:

[0050] Firstly, the historical long-series ten-day runoff data of the target reservoir station are estimated using existing standard methods, including the runoff correlation method and the hydrological analogy method.

[0051] Then, considering the nonlinear characteristics of the actual runoff generation and runoff process, a machine learning model that can handle nonlinear correspondence is introduced to correct the estimated historical long series of ten-day runoff data to improve the estimation accuracy.

[0052] Finally, the corrected historical long series of ten-day runoff data are time-downscaled to obtain the long series of daily runoff data of the target reservoir station.

[0053] See also Figure 1 , which is a flow chart of the reservoir daily runoff historical series estimation method integrated with machine learning correction in this application. Figure 1 Describe the specific implementation of this application in detail, the steps are as follows:

[0054] S100: Based on the short series measured runoff data of the target reservoir station and the long series measured runoff data of the reference station, the historical long series ten-day runoff data of the target reservoir station are estimated by using the runoff correlation method and the hydrological analogy method, which are recorded as the first long series estimated ten-day runoff data and the second long series estimated ten-day runoff data respectively;

[0055] The reference station refers to the reference station of the target reservoir. The selection of the reference station is a conventional technology in the industry. The selected reference station should meet the following two points at the same time: ① The basin where the reference station is located is the upstream, downstream or adjacent basin of the reservoir basin; ② The basin where the reference station is located has a long series of measured runoff data. Here, the reservoir basin refers to the basin where the target reservoir is located.

[0056] In this specific implementation, the method for selecting the reference station is:

[0057] First, the upstream, downstream and adjacent basins with long series of measured runoff data are obtained and recorded as potential reference basins; the upstream, downstream and adjacent basins here refer to the upstream, downstream or adjacent basins of the reservoir basin;

[0058] Then, a basin with similar rainfall and underlying surface characteristics to the reservoir basin is selected from the potential reference basins as the reference basin, and the hydrological station in the reference basin is the reference station. The underlying surface characteristics include but are not limited to the topography and vegetation of the basin.

[0059] S200: Use the machine learning model to correct the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data to obtain the corrected historical long series of ten-day runoff data for the target reservoir station;

[0060] This step mainly includes two parts: using training samples to train the machine learning model and using the trained machine learning model to correct the estimated historical long series of ten-day runoff data.

[0061] In this specific implementation, training a machine learning model using training samples further includes:

[0062] S210: construct a sample data set, the sample data set includes a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data in the same period; divide the sample data set into a training sample set and a test sample set, wherein the sample data set is used to train the machine learning model, and the test sample set is used to test the machine learning model; the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data in the same period, wherein "the same period" refers to the same period as the short series of measured ten-day runoff data;

[0063] S220: training the machine learning model using the training sample set; specifically, using the short series of measured ten-day runoff data of the target reservoir station as output, and using the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data of the same period as input, the structure and parameters of the machine learning model are trained and calibrated;

[0064] The machine learning model is represented as follows:

[0065] Q ml,旬 =f(Q 1,旬 +Q 2,旬 ) (1)

[0066] In formula (1):

[0067] f() represents the machine learning model function;

[0068] Q ml , 旬 Represents the historical long series of ten-day runoff data after correction by the machine learning model;

[0069] Q 1,旬 It represents the first long series of estimated ten-day runoff data estimated by the runoff correlation method;

[0070] Q 2,旬 Represents the second longest series of estimated ten-day runoff data using the hydrological analogy method.

[0071] S230: Using a test sample set to test the trained machine learning model;

[0072] In this specific implementation, at least two of the support vector machine model, random forest model, gradient boosting regression tree model, long short-term memory network model, etc. are selected for training respectively, and then a test sample set is used to test the trained multiple machine learning models to select the machine learning model with the highest accuracy.

[0073] In this specific embodiment, the use of the trained machine learning model to correct the estimated historical long series of ten-day runoff data further includes: inputting the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data into the trained machine learning model, and then outputting the corrected historical long series of ten-day runoff data Q ml,旬 .

[0074] Furthermore, according to the relative deviation of water volume, the corrected historical long series of ten-day runoff data Q ml,旬 Make corrections to further improve accuracy.

[0075] Specifically, the historical long series of ten-day runoff data Q ml,旬 The correction formula is as follows:

[0076]

[0077] In formula (2):

[0078] Q' ml,旬 It represents the revised historical long series of ten-day runoff data;

[0079] n represents the number of ten days of short series measured runoff data at the target reservoir station;

[0080] Indicates the short series of measured ten-day runoff at the target reservoir station the sum of represents the measured ten-day runoff in the i-th short series;

[0081] It indicates that the corrected historical long series of ten-day runoff The sum of runoff during the same period.

[0082] S300: time downscaling the corrected historical long series of ten-day runoff data to obtain the long series of daily runoff data of the target reservoir station;

[0083] Determine whether there is rainfall in the current ten-day period. If there is no rainfall, the current ten-day runoff is all underground runoff. If there is rainfall, the current ten-day runoff is divided into underground runoff and surface runoff in proportion according to the current ten-day rainfall. For underground runoff, time downscaling is performed based on the equal runoff volume every day within the ten-day period to obtain daily underground runoff. For surface runoff, time downscaling is performed based on the change process of other hydrological and meteorological factors with daily resolution information (such as the daily runoff process of the reference station, the daily rainfall process of the reservoir basin, etc.) to obtain daily surface runoff. Finally, the daily underground runoff and daily surface runoff on the same day are added to obtain the daily runoff data.

[0084] Specifically, the time downscaling formula is as follows:

[0085]

[0086]

[0087]

[0088]

[0089] In formulas (3) to (6):

[0090] and represent ten-day underground runoff and ten-day surface runoff respectively;

[0091] P 目标,旬 It indicates the ten-day rainfall in the reservoir basin;

[0092] k represents the distribution coefficient of groundwater runoff. This value is an empirical value determined by referring to the ratio of the average surface water resources and groundwater resources in the reference basin over many years. For the humid areas in the south, the distribution coefficient k is generally taken as 0.1;

[0093] and They represent the daily underground runoff and daily surface runoff on the i-th day of the current decade respectively;

[0094] P 目标,i It represents the daily rainfall in the reservoir basin on the i-th day of the current ten-day period;

[0095] Q' ml,i It represents the historical long series daily runoff data after time downscaling;

[0096] n represents the total number of days in the current decade.

[0097] The technical effects of the present application will be further explained below with reference to embodiments.

[0098] In this example, there is a hydrological station A on the river near the target reservoir. The rainfall and underlying surface characteristics of the basin where the hydrological station A is located are similar to those of the basin where the target reservoir is located. Hydrological station A has a long series of continuous measured runoff data from 1983 to 2023. Therefore, hydrological station A is selected as the reference station for the target reservoir.

[0099] Based on the long series of measured runoff data of the reference station and the short series of measured runoff data of the target reservoir station, the runoff correlation method and the hydrological analogy method are used to estimate the historical long series of ten-day runoff data of the target reservoir station, which are recorded as the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data, respectively. The short series of measured runoff data of the target reservoir station is compared with the runoff data of the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data during the same period. For comparison, see Figure 2 In the figure, "measured" represents the short series of measured runoff data of the target reservoir station, "Series 1" and "Series 2" represent the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data, respectively; and the accuracy of the runoff correlation method and the hydrological analogy method for the same period is evaluated, and the accuracy data is shown in Table 1.

[0100] Table 1 Accuracy of runoff data estimated by runoff correlation method and hydrological analogy method in the same period

[0101]

[0102]

[0103] The short series of measured ten-day runoff data of the target reservoir station and the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data of the same period are used to construct a sample data set, and 2020-2022 is selected as the training period, and 2019 is selected as the test period. The ten-day runoff data estimated during the training period is used as the input of the machine learning model, and the short series of measured ten-day runoff data of the target reservoir station during the training period is used as the output of the machine learning model to train the machine learning model. In this embodiment, four different machine learning models are selected for training respectively, including a support vector machine model, a random forest model, a gradient boosting regression tree model, and a long short-term memory network model.

[0104] The trained machine learning model was used to calibrate and correct the estimated ten-day runoff data during the training period and the test period, and the corrected ten-day runoff data were compared with the short series of measured ten-day runoff data of the target reservoir station during the test period. Figures 3-4In the figure, "measured" represents the short series of measured ten-day runoff data of the target reservoir station, "support vector machine" represents the ten-day runoff data corrected by the support vector machine model, "random forest" represents the ten-day runoff data corrected by the random forest model, "gradient boosting regression tree" represents the ten-day runoff data corrected by the gradient boosting regression tree model, and "long short-term memory" represents the ten-day runoff data corrected by the long short-term memory network model; and evaluate the accuracy of the estimated runoff in the same period after correction by the machine learning model. The accuracy data of different machine learning models are shown in Table 2. Figures 3-4 As shown in Table 2, the accuracy of the ten-day runoff data after correction by the gradient boosting regression tree model is the highest.

[0105] Table 2 Accuracy of runoff estimation in the same period after correction by four machine learning models

[0106]

[0107] The historical long-series ten-day runoff data after correction by the gradient boosting regression tree model were downscaled to infer the historical long-series daily runoff data of the target reservoir station and compared with the short-series measured daily runoff data of the target reservoir station. Figure 5 As shown. The frequency analysis of the estimated long series daily runoff data of the target reservoir station and the long series measured daily runoff data of the reference station is performed, and the results of the frequency analysis are shown in Table 3. The reservoir basin is located upstream of the reference basin, and the ratio of the reservoir basin area to the reference basin area is 43.62%. After comparison, the ratio of the long series runoff mean of the reservoir basin and the average flow at each frequency to the reference station is between 46.21% and 47.83%, which is greater than the area ratio of the reservoir basin to the reference basin, which is consistent with the trend that the basin rainfall center is close to the upstream reservoir area and the rainfall decreases from upstream to downstream. In addition, the long series runoff variation coefficient Cv of the target reservoir station and the reference station are 0.23 and 0.24, respectively, which is consistent with the basin similarity judgment.

[0108] Table 3 Frequency analysis results of long series daily runoff data of target reservoir station and reference station

[0109]

[0110] The annual average runoff of the reservoir basin can be calculated using the estimated long series daily runoff data of the target reservoir station. According to the MK test, the annual rainfall in the reservoir basin has a continuous upward trend since 1991, and the annual average runoff has also a continuous upward trend since 1991. The annual average runoff of the reservoir basin from 1983 to 2022 is consistent with the change trend of annual rainfall. Figure 6 .

[0111] In combination with the above embodiments, it can be concluded that: when the reservoir basin runoff series is short, the use of the method of the present application can significantly improve the estimation accuracy and time resolution of the long series of reservoir runoff data, and the calculated runoff series results are reasonable.

[0112] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present application, all of which belong to the protection scope of the present application.

Claims

1. A method for estimating reservoir daily runoff history series by integrating machine learning correction, characterized in that: include: S100: Based on the short series measured runoff data of the target reservoir station and the long series measured runoff data of the reference station, the historical long series ten-day runoff data of the target reservoir station are estimated by using the runoff correlation method and the hydrological analogy method, which are recorded as the first long series estimated ten-day runoff data and the second long series estimated ten-day runoff data respectively; S200: Use the machine learning model to correct the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data to obtain the corrected historical long series of ten-day runoff data for the target reservoir station; The machine learning model is first trained using training samples, wherein the training samples include a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data of the same period; The machine learning model is trained using the short series of measured ten-day runoff data of the target reservoir station as output and the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data of the same period as input; S300: Time downscaling the corrected historical long series of ten-day runoff data to obtain the long series of daily runoff data of the target reservoir station.

2. The method for estimating reservoir daily runoff history series by integrating machine learning correction as claimed in claim 1 is characterized by: The machine learning model is first trained using training samples, further comprising: S210: constructing a sample data set, wherein the sample data set includes a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data of the same period; dividing the sample data set into a training sample set and a test sample set; S220: training the machine learning model using the training sample set; S230: Using a test sample set to test the trained machine learning model; Select a variety of different machine learning models for training and testing respectively, and use the machine learning model with the highest accuracy for calibration.

3. The method for estimating reservoir daily runoff history series by integrating machine learning correction as claimed in claim 1 or 2, characterized in that: The machine learning model is one or more of a support vector machine model, a random forest model, a gradient boosting regression tree model, and a long short-term memory network model.

4. The method for estimating reservoir daily runoff history series by integrating machine learning correction as claimed in claim 1 is characterized by: Step S200 also includes: The corrected historical long series of ten-day runoff data are corrected according to the relative deviation of water volume: Among them, Q' ml,旬 represents the corrected historical long-series ten-day runoff data; n represents the ten-day number of the short-series measured runoff data of the target reservoir station; Indicates the short series of measured ten-day runoff at the target reservoir station the sum of represents the measured ten-day runoff in the i-th short series; It indicates that the corrected historical long series of ten-day runoff The sum of runoff during the same period.

5. The method for estimating reservoir daily runoff history series by integrating machine learning correction as claimed in claim 1, characterized in that: Step S300 further includes: The following are performed on the runoff of each decade in the corrected historical long series of runoff data: Determine whether there is rainfall in the current ten-day period. If there is no rainfall, the current ten-day runoff is underground runoff. If there is rainfall, the current ten-day runoff is divided into underground runoff and surface runoff in proportion according to the rainfall in the current ten-day period. For underground runoff, the daily underground runoff is obtained by time downscaling based on the equal runoff volume every day within ten days; For surface runoff, Time downscaling is performed to obtain the daily surface runoff Among them, n represents the total number of days in the current decade, represents the surface runoff in the current decade, P 目标,i represents the rainfall in the reservoir basin on the i-th day of the current ten-day period, It indicates the total rainfall in the reservoir basin in the current decade; For the current decade without rainfall, the daily groundwater runoff is the daily runoff data; For the current decade with rainfall, the daily groundwater runoff and daily surface runoff on the same day are added together to obtain the daily runoff data.

6. A reservoir daily runoff history series estimation system integrating machine learning correction, characterized by: include: The first module is used to estimate the historical long-series ten-day runoff data of the target reservoir station based on the short-series measured runoff data of the target reservoir station and the long-series measured runoff data of the reference station, respectively using the runoff correlation method and the hydrological analogy method, which are recorded as the first long-series estimated ten-day runoff data and the second long-series estimated ten-day runoff data; The second module is used to use the machine learning model to correct the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data to obtain the corrected historical long series of ten-day runoff data for the target reservoir station; The machine learning model is first trained using training samples, wherein the training samples include a short series of measured ten-day runoff data of the target reservoir station and a first long series of estimated ten-day runoff data and a second long series of estimated ten-day runoff data of the same period; The machine learning model is trained using the short series of measured ten-day runoff data of the target reservoir station as output and the first long series of estimated ten-day runoff data and the second long series of estimated ten-day runoff data of the same period as input; The third module is used to time downscale the corrected historical long series of ten-day runoff data to obtain the long series of daily runoff data of the target reservoir station.

7. The reservoir daily runoff history series estimation system integrating machine learning correction as claimed in claim 6 is characterized by: The machine learning model is a support vector machine model, a random forest model, a gradient boosting regression tree model or a long short-term memory network model.

8. The reservoir daily runoff history series estimation system integrating machine learning correction as claimed in claim 6 is characterized by: The second module also includes a correction submodule, which is used to correct the corrected historical long series of ten-day runoff data according to the relative deviation of water volume: Among them, Q' ml,旬 represents the corrected historical long-series ten-day runoff data; n represents the ten-day number of the short-series measured runoff data of the target reservoir station; Indicates the short series of measured ten-day runoff at the target reservoir station the sum of represents the measured ten-day runoff in the i-th short series; It indicates that the corrected historical long series of ten-day runoff The sum of runoff during the same period.

9. The reservoir daily runoff history series estimation system integrating machine learning correction as claimed in claim 6 is characterized by: The third module further comprises: Submodule 1 is used to determine whether there is rainfall in the current ten-day period. If there is no rainfall, the current ten-day runoff is underground runoff. If there is rainfall, the current ten-day runoff is divided into underground runoff and surface runoff in proportion according to the rainfall in the current ten-day period. Submodule 2 is used to downscale the underground runoff to obtain the daily underground runoff according to the equal runoff volume every day within ten days; Submodule 3 is used to analyze surface runoff according to Time downscaling is performed to obtain the daily surface runoff Among them, n represents the total number of days in the current decade, represents the surface runoff in the current decade, P 目标,i represents the rainfall in the reservoir basin on the i-th day of the current ten-day period, It indicates the total rainfall in the reservoir basin in the current decade; Submodule 4 is used to obtain the daily underground runoff data for the current decade without rainfall; for the current decade with rainfall, the daily underground runoff and the daily surface runoff on the same day are added to obtain the daily runoff data.

Images