A method for identifying factors affecting water level and flow relationship, storage medium and computer equipment

Abstract

The present invention discloses a method for identifying factors affecting the relationship between water level and flow, comprising: obtaining water level and flow data at the current moment and the previous two moments of a target site and upstream and downstream adjacent sites; preprocessing the water level and flow data at the current moment and the previous two moments to obtain a preprocessing result; the preprocessing result comprises: the water level, the fluctuation rate and the relative error of a single curve of the target site at the current moment, and the water level of the upstream and downstream adjacent sites; using a trained SVM model, classifying and identifying factors affecting the relationship between water level and flow at the current moment based on the preprocessing result, and obtaining an identification result of the factors affecting the relationship between water level and flow at the current moment; the present invention can realize the real-time identification and classification of factors affecting the relationship between water level and flow more quickly and accurately, and can improve the accuracy and applicability of the water level and flow relationship curve.

Description

Technical Field

[0001] The invention relates to a method for identifying factors affecting the relationship between water level and flow rate, a storage medium and a computer device, and belongs to the technical field of hydrological testing. Background Art

[0002] The water level-flow relationship refers to the relationship between the flow rate of a certain section in a river and the corresponding water level. The water level-flow relationship is determined by various hydraulic factors and can be described by the Saint-Venant equations. The complete Saint-Venant equation has no analytical solution, and the river water level-flow relationship can only be described by simplified functions, empirical curves or other indirect mapping relationships. The relationship between water level and flow in natural rivers is sometimes a stable single-valued function relationship, and sometimes affected by multiple factors, such as flood fluctuations, variable backwater, etc., and presents a noose curve relationship.

[0003] The relationship between water level and flow is the key to the compilation of hydrological data. Its accuracy and rationality directly affect the reliability of the compilation of hydrological data. At present, the relationship between water level and flow is mainly drawn by hydrological experts in combination with the characteristics of the measuring station, water conditions, water level drop and other information. It mainly relies on the hydrological knowledge and experience of hydrological experts and has low accuracy. At the same time, the drawing of the relationship between water level and flow is generally combined with the entire flood rise and fall process, upstream and downstream flood processes, etc., and is generally finalized at the end of the year, with poor timeliness. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method for identifying factors affecting the relationship between water level and flow, a storage medium and a computer device. Based on the learning of a large amount of data using an SVM model, features and association rules are automatically extracted, and the factors affecting the relationship between water level and flow at the current moment are classified and identified. This method can more quickly and accurately realize real-time identification and classification of factors affecting the relationship between water level and flow, and can improve the accuracy and applicability of the water level-flow relationship curve.

[0005] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0006] In a first aspect, the present invention provides a method for identifying factors affecting the relationship between water level and flow, comprising:

[0007] Obtain the water level and flow data of the target site and the upstream and downstream adjacent sites at the current time and the previous two times;

[0008] Preprocessing the water level flow data at the current moment and the previous two moments to obtain preprocessing results; the preprocessing results include: the water level, fluctuation rate and single curve relative error of the target site at the current moment, and the water levels of upstream and downstream adjacent sites;

[0009] The trained SVM model is used to classify and identify the factors affecting the relationship between the water level and flow at the current moment based on the preprocessing results, so as to obtain the identification results of the factors affecting the relationship between the water level and flow at the current moment.

[0010] Optionally, a method for obtaining the fluctuation rate of the target site at the current moment includes:

[0011] Based on the water level flow data at the current moment and the previous two moments, obtaining the water level data of the target site at the current moment and the previous moment;

[0012] The water level data of the target site at the current moment and the previous moment are linearly fitted to obtain the rise and fall rate of the target site at the current moment.

[0013] Optionally, a method for obtaining the relative error of a single curve of the target site at the current moment includes:

[0014] Based on the water level flow data at the current moment and the previous two moments, obtain relevant data of the water level of the target site at the current moment and the previous two moments, the relevant data including lnZ(t), (lnZ(t)) 2 、(lnZ(t)) 3 ;

[0015] Based on the water level flow data at the current moment and the previous two moments, calculate the water level difference between the target site and the upstream and downstream adjacent sites at the current moment and the previous two moments respectively;

[0016] The relevant data of the target site water level at the current moment and the previous two moments and the water level difference between the target site and the upstream and downstream adjacent sites are input into the trained LSTM model to obtain the calculated flow rate Q at the current moment t ;

[0017] The relevant data of the target site water level at the current moment and the previous two moments are input into the trained LSTM model to obtain the single curve flow Q at the current moment. 0 ;

[0018] Calculate the flow rate Q based on the current time t and single curve flow Q 0 , calculate the relative error of a single curve at the current moment.

[0019] Optionally, the formula for calculating the relative error S of a single curve at the current moment is as follows:

[0020]

[0021] Where: Q t is the calculated flow at the current moment, Q 0 is the single curve flow at the current moment.

[0022] Optionally, the method for obtaining the trained LSTM model includes:

[0023] Obtain water level and flow data of the target site and upstream and downstream adjacent sites over a period of time;

[0024] Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within the period of time, obtain the relevant data of the water level Z(t) of the target site at each moment;

[0025] Based on the water level flow data of the target site and the upstream and downstream adjacent sites within the period of time, the water level difference ΔZ(t) between the target site and the upstream and downstream adjacent sites at each moment is calculated;

[0026] Get the measured flow rate Q(t);

[0027] Based on the measured flow Q(t), relevant data of the water level Z(t) at the target site and the water level difference ΔZ(t), the LSTM model is trained to obtain a trained LSTM.

[0028] Optionally, the method for obtaining the trained SVM model includes:

[0029] Obtain water level and flow data of the target site and upstream and downstream adjacent sites within three years;

[0030] Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within three years, determine the rise and fall rate of the target site at each moment;

[0031] Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within three years, the water level and flow data of the target site within three years are polynomially fitted to obtain a single curve, and the relative error of the single curve at each moment is calculated;

[0032] Based on the fluctuation rate of the target site at each moment and the relative error of a single curve at each moment, the factors affecting the relationship between the water level and the flow rate at each moment are classified and identified to obtain the factors affecting the relationship between the water level and the flow rate at each moment;

[0033] The water levels of the target site and the upstream and downstream adjacent sites at each moment in three years, the rise and fall rate of the target site at each moment and the relative error of the single curve at each moment are taken as input features, and the influencing factors of the water level-flow relationship at each moment are taken as labels. After dividing the training set and the test set, they are input into the SVM model for training to obtain the trained SVM model.

[0034] Optionally, the classification and identification of factors affecting the relationship between water level and flow at each moment includes:

[0035] Set the threshold T;

[0036] The moment when the relative error of a single curve is less than a threshold value T is divided into a stable relationship segment, and the stable relationship segment is not affected by flood fluctuations and variable backwater;

[0037] For the moment when the relative error of a single curve is greater than the threshold T, the moment when the flow rate of the target site is greater than the flow rate corresponding to the single curve and the fluctuation rate is positive is divided into the flood rising and falling section; the moment when the flow rate of the target site is less than the flow rate corresponding to the single curve and the fluctuation rate is negative is divided into the flood rising and falling section; the moment when the flow rate of the target site is less than the flow rate corresponding to the single curve and the fluctuation rate is positive is divided into the variable backwater rising section; the moment when the flow rate of the target site is greater than the flow rate corresponding to the single curve and the fluctuation rate is negative is divided into the variable backwater falling section.

[0038] Optionally, using the trained SVM model, based on the preprocessing result, the factors affecting the relationship between the water level and the flow at the current moment are classified and identified to obtain the identification results of the factors affecting the relationship between the water level and the flow at the current moment, including:

[0039] The current water level, fluctuation rate and relative error of a single curve of the target station, as well as the water levels of the upstream and downstream adjacent stations are input into the trained SVM model;

[0040] Based on the process of classifying and identifying the factors affecting the water level-flow relationship at each moment, the factors affecting the water level-flow relationship at the current moment are classified and identified to obtain the identification results of the factors affecting the water level-flow relationship at the current moment.

[0041] In a second aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method for identifying factors affecting the water level-flow relationship described in the first aspect are implemented.

[0042] In a third aspect, the present invention provides a computer device, characterized in that it includes:

[0043] A memory for storing instructions;

[0044] The processor is used to execute the instructions so that the device executes the method for identifying the factors affecting the water level-flow relationship described in the first aspect.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention proposes a method for identifying factors affecting the relationship between water level and flow, a storage medium and a computer device. Based on the learning of a large amount of data using an SVM model, features and association rules are automatically extracted, and the factors affecting the relationship between water level and flow at the current moment are classified and identified. This method can more quickly and accurately realize real-time identification and classification of factors affecting the relationship between water level and flow, and can improve the accuracy and applicability of a water level-flow relationship curve. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor, among which:

[0048] Figure 1 Shown is a flow chart of a method for identifying factors affecting the relationship between water level and flow rate according to the present invention;

[0049] Figure 2 It is a schematic diagram of manual classification in the method for identifying factors affecting the relationship between water level and flow rate of the present invention;

[0050] Figure 3 Shown is the water level-flow relationship curve in 2020 after SVM model classification;

[0051] Figure 4 Shown is the water level process line diagram in 2020 after classification by the SVM model. DETAILED DESCRIPTION

[0052] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0053] The application principle of the present invention is described in detail below in conjunction with the accompanying drawings.

[0054] Example 1

[0055] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying factors affecting the relationship between water level and flow, comprising:

[0056] S01: Obtain the water level and flow data of the target site and the upstream and downstream adjacent sites at the current time and the previous two times;

[0057] S02: preprocessing the water level flow data at the current moment and the previous two moments to obtain a preprocessing result; the preprocessing result includes: the water level, fluctuation rate and single curve relative error of the target site at the current moment, and the water levels of the upstream and downstream adjacent sites;

[0058] S03: Using the trained SVM (support vector machine) model, based on the preprocessing results, classify and identify the factors affecting the relationship between the water level and flow at the current moment, and obtain the identification results of the factors affecting the relationship between the water level and flow at the current moment.

[0059] The method for identifying factors affecting the water level-flow relationship in the embodiment of the present invention can more quickly and accurately realize real-time identification and classification of factors affecting the water level-flow relationship, and can improve the accuracy and applicability of the water level-flow relationship curve.

[0060] In a specific implementation of the embodiment of the present invention, in step S02, the specific steps of obtaining the preprocessing result include:

[0061] S021: directly obtain the water level of the target site at the current moment and the water levels of the upstream and downstream adjacent sites according to the water level flow data at the current moment and the previous two moments in step S01;

[0062] S022: Obtain the water level data of the target site at the current moment and the previous moment according to the water level flow data at the current moment and the previous two moments in step S01;

[0063] Linear fitting is performed on the water level data of the target site at the current moment and the previous moment to obtain the fluctuation rate of the target site at the current moment. The fluctuation rate formula is as follows:

[0064]

[0065] Among them: k is the fluctuation rate of the target site at the current moment, Z t is the water level data of the target site at the current moment, Z t-1 It is the water level data of the target site at the previous moment.

[0066] S023: Based on the water level flow data at the current moment and the previous two moments in step S01, and using the trained LSTM model, obtain the calculated flow Q at the current moment t and single curve flow Q 0 , and calculate the relative error of a single curve at the current moment.

[0067] In a specific implementation of the embodiment of the present invention, the specific steps of calculating the relative error of a single curve at the current moment in step S023 include:

[0068] S231: Obtain water level and flow data of the target site and upstream and downstream adjacent sites within a period of time;

[0069] S232: Based on the water level and flow data in step S231, obtain the relevant data of the water level Z(t) of the target station at each moment; specifically, the relevant data is expressed as: taking the square and cube of the natural logarithm of the water level of the target station at each moment, i.e., lnZ(t), (lnZ(t)) 2 、(lnZ(t)) 3 ;

[0070] S233: Based on the water level flow data in step S231, the water level difference ΔZ(t) between the target site and the upstream and downstream adjacent sites at each moment is calculated;

[0071] S234: Obtaining the measured flow rate Q(t);

[0072] S235: Based on the measured flow Q(t), the relevant data of the water level Z(t) of the target site and the water level difference ΔZ(t), the LSTM model (Long Short-Term Memory Network Model) is trained to obtain a trained LSTM;

[0073] S236: Obtain relevant data of the water level of the target site at the current moment and the previous two moments;

[0074] S237: Calculate the water level difference between the target site and the upstream and downstream adjacent sites at the current moment and the previous two moments;

[0075] S238: Input the relevant data of the target site water level at the current moment and the previous two moments and the water level difference between the target site and the upstream and downstream adjacent sites into the trained LSTM model to obtain the calculated flow rate Q at the current moment t ;

[0076] The relevant data of the target site water level at the current moment and the previous two moments are input into the trained LSTM model to obtain the single curve flow Q at the current moment. 0 ;

[0077] Calculate the flow rate Q based on the current time t and single curve flow Q 0 , calculate the relative error S of a single curve at the current moment, the formula is as follows:

[0078]

[0079] In a specific implementation of the embodiment of the present invention, the method for obtaining the trained SVM model in step S02 includes:

[0080] S11: Obtain water level and flow data of the target site and upstream and downstream adjacent sites within three years; specifically, collect the hydrological element abstract table of the target site and its upstream and downstream adjacent sites, and perform linear interpolation on the water level and flow data (2018-2020) on the hydrological element abstract table so that the time step of the site water level and flow data is one hour;

[0081] S12: Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within three years, determine the rise and fall rate of the target site at each moment (each time point); specifically, the process of calculating the rise and fall rate of the target site at a certain moment is: take the data of a certain moment and two moments before and after, perform linear fitting on these five data, and calculate the slope, that is, the rise and fall rate at the moment;

[0082] S13: Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within three years, the water level and flow data of the target site within three years are polynomially fitted to obtain a single curve, and the relative error of the single curve at each moment is calculated, that is, the relative error between the actual flow value corresponding to the water level at each time point of the target site and the flow corresponding to the water level in the single curve is calculated;

[0083] S14: Based on the fluctuation rate of the target site at each moment and the relative error of the single curve at each moment, the factors affecting the relationship between the water level and the flow at each moment are classified and identified (manual classification), the factors affecting the relationship between the water level and the flow are divided, and an SVM model (support vector machine model) is constructed according to the data after manual classification;

[0084] Specifically, the manual classification process, such as Figure 2 As shown, a threshold T is set; in this embodiment, the threshold T is set to 3%;

[0085] The moment when the relative error of a single curve is less than a threshold value T is divided into a stable relationship segment, and the stable relationship segment is not affected by flood fluctuations and variable backwater;

[0086] For the moment when the relative error of a single curve is greater than the threshold T, the moment when the flow rate of the target site is greater than the flow rate corresponding to the single curve (the flow rate is located on the right side of the single curve) and the fluctuation rate is positive is divided into the flood fluctuation and rising water section; the moment when the flow rate of the target site is less than the flow rate corresponding to the single curve (the flow rate is located on the left side of the single curve) and the fluctuation rate is negative is divided into the flood fluctuation and falling water section; the moment when the flow rate of the target site is less than the flow rate corresponding to the single curve (the flow rate is located on the left side of the single curve) and the fluctuation rate is positive is divided into the variable backwater rising water section; the moment when the flow rate of the target site is greater than the flow rate corresponding to the single curve (the flow rate is located on the right side of the single curve) and the fluctuation rate is negative is divided into the variable backwater falling water section.

[0087] S15 is based on the results of classification and identification processing (manual classification) of the factors affecting the relationship between water level and flow at each moment. The water level of the target site and the upstream and downstream adjacent sites at each moment in three years, the rise and fall rate of the target site at each moment, and the relative error of the single curve at each moment are used as input features. The factors affecting the relationship between water level and flow at each moment are used as labels. After dividing the set into training and test sets, the SVM model is input for training to obtain the trained SVM model.

[0088] In a specific implementation of the embodiment of the present invention, the step of obtaining the identification result of the influencing factor of the water level flow relationship at the current moment includes:

[0089] The current water level, fluctuation rate and relative error of a single curve of the target station, as well as the water levels of the upstream and downstream adjacent stations are input into the trained SVM model;

[0090] Based on the process of classifying and identifying the factors affecting the water level-flow relationship at each moment, the factors affecting the water level-flow relationship at the current moment are classified and identified to obtain the identification results of the factors affecting the water level-flow relationship at the current moment.

[0091] In a specific implementation of an embodiment of the present invention, the factors affecting the relationship between water level and flow in 2020 are identified and classified, and the specific steps include:

[0092] Obtain water level and flow data for the target site and adjacent sites upstream and downstream in 2020;

[0093] The water level and flow data in 2020 are preprocessed to obtain preprocessing results; the preprocessing results include: the water level, the fluctuation rate and the relative error of a single curve at each moment in 2020, and the water levels of adjacent stations upstream and downstream;

[0094] By using the SVM model trained by the present invention, the factors affecting the relationship between the water level and flow in 2020 are classified and identified based on the preprocessing results, and the identification results of the factors affecting the relationship between the water level and flow in 2020 are obtained.

[0095] like Figure 3 and Figure 4 Shown is the water level-flow relationship curve and water level process line diagram in 2020 after SVM model classification, indicating that the identification method of the present invention can more accurately identify and classify the factors affecting the water level-flow relationship.

[0096] Example 2

[0097] In this embodiment, the present invention further introduces a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for identifying factors affecting the relationship between water level and flow rate as described in Example 1 are implemented.

[0098] Example 3

[0099] In this embodiment, the present invention further introduces a computer device, including:

[0100] A memory for storing instructions;

[0101] The processor is used to execute the instructions so that the device performs operations to implement the method for identifying factors affecting the water level-flow relationship as described in Example 1.

[0102] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method for identifying factors affecting the relationship between water level and flow, characterized in that: include: Obtain the water level and flow data of the target site and the upstream and downstream adjacent sites at the current time and the previous two times; Preprocessing the water level flow data at the current moment and the previous two moments to obtain a preprocessing result; The preprocessing results include: the water level, fluctuation rate and single curve relative error of the target site at the current moment, and the water levels of the upstream and downstream adjacent sites; The method for obtaining the fluctuation rate of the target site at the current moment includes: Based on the water level flow data at the current moment and the previous two moments, obtaining the water level data of the target site at the current moment and the previous moment; Performing linear fitting on the water level data of the target site at the current moment and the previous moment to obtain the rise and fall rate of the target site at the current moment; The method for obtaining the relative error of a single curve of the target site at the current moment includes: Based on the water level flow data at the current moment and the previous two moments, obtain relevant data of the water level of the target site at the current moment and the previous two moments, the relevant data including lnZ(t), (lnZ(t)) 2 、(lnZ(t)) 3 ; Based on the water level flow data at the current moment and the previous two moments, calculate the water level difference between the target site and the upstream and downstream adjacent sites at the current moment and the previous two moments respectively; The relevant data of the target site water level at the current moment and the previous two moments and the water level difference between the target site and the upstream and downstream adjacent sites are input into the trained LSTM model to obtain the calculated flow rate Q at the current moment t ; The relevant data of the water level of the target site at the current moment and the previous two moments are input into the trained LSTM model to obtain the single curve flow Q0 at the current moment; Calculate the flow rate Q based on the current time t and the single curve flow Q0, calculate the single curve relative error at the current moment; The formula for calculating the relative error S of a single curve at the current moment is as follows: Where: Q t is the calculated flow at the current moment, Q0 is the single curve flow at the current moment; The method for obtaining the trained LSTM model includes: Obtain water level and flow data of the target site and upstream and downstream adjacent sites over a period of time; Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within the period of time, obtain the relevant data of the water level Z(t) of the target site at each moment; Based on the water level flow data of the target site and the upstream and downstream adjacent sites within the period of time, the water level difference ΔZ(t) between the target site and the upstream and downstream adjacent sites at each moment is calculated; Get the measured flow rate Q(t); Based on the measured flow Q(t), the relevant data of the water level Z(t) at the target site and the water level difference ΔZ(t), the LSTM model is trained to obtain a trained LSTM; Using the trained SVM model, based on the preprocessing results, the factors affecting the relationship between the water level and the flow at the current moment are classified and identified to obtain the identification results of the factors affecting the relationship between the water level and the flow at the current moment; The method for obtaining the trained SVM model includes: Obtain water level and flow data of the target site and upstream and downstream adjacent sites within three years; Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within three years, determine the rise and fall rate of the target site at each moment; Based on the water level and flow data of the target site and the upstream and downstream adjacent sites within three years, the water level and flow data of the target site within three years are polynomially fitted to obtain a single curve, and the relative error of the single curve at each moment is calculated; Based on the fluctuation rate of the target site at each moment and the relative error of a single curve at each moment, the factors affecting the relationship between the water level and the flow rate at each moment are classified and identified to obtain the factors affecting the relationship between the water level and the flow rate at each moment; The water levels of the target site and the upstream and downstream adjacent sites at each moment in three years, the fluctuation rate of the target site at each moment and the relative error of the single curve at each moment are used as input features, and the influencing factors of the water level-flow relationship at each moment are used as labels. After dividing the training set and the test set, the SVM model is input for training to obtain the trained SVM model. The classification and identification of the factors affecting the relationship between water level and flow at each moment includes: Set the threshold T; The moment when the relative error of a single curve is less than a threshold value T is divided into a stable relationship segment, and the stable relationship segment is not affected by flood fluctuations and variable backwater; For the moment when the relative error of a single curve is greater than the threshold T, the moment when the flow rate of the target site is greater than the flow rate corresponding to the single curve and the fluctuation rate is positive is divided into the flood rising and falling section; the moment when the flow rate of the target site is less than the flow rate corresponding to the single curve and the fluctuation rate is negative is divided into the flood rising and falling section; the moment when the flow rate of the target site is less than the flow rate corresponding to the single curve and the fluctuation rate is positive is divided into the variable backwater rising section; the moment when the flow rate of the target site is greater than the flow rate corresponding to the single curve and the fluctuation rate is negative is divided into the variable backwater falling section.

2. The method for identifying factors affecting the relationship between water level and flow rate according to claim 1, characterized in that: Using the trained SVM model, based on the preprocessing results, the factors affecting the relationship between the water level and the flow at the current moment are classified and identified to obtain the identification results of the factors affecting the relationship between the water level and the flow at the current moment, including: The current water level, fluctuation rate and relative error of a single curve of the target station, as well as the water levels of the upstream and downstream adjacent stations are input into the trained SVM model; Based on the process of classifying and identifying the factors affecting the water level-flow relationship at each moment, the factors affecting the water level-flow relationship at the current moment are classified and identified to obtain the identification results of the factors affecting the water level-flow relationship at the current moment.

3. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying factors affecting the relationship between water level and flow rate as described in any one of claims 1 to 2 are implemented.

4. A computer device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instruction so that the device executes the method for identifying factors affecting the relationship between water level and flow as described in any one of claims 1-2.

Images