A runoff prediction method, device, and storage medium

Abstract

The present invention discloses a runoff prediction method, device, and storage medium. The runoff prediction method includes: calculating the dynamic response characteristics of each moment and each grid cell by using meteorological inputs; extracting the static influence characteristics of static attributes on runoff errors; extracting the characteristics that simultaneously reflect temporal and spatial influences to obtain an error correction amount generated based on meteorological inputs and underlying surface information; constructing a reservoir operation alternative network to output the correction component of reservoir operation on runoff; constructing a loss function, superimposing the above correction component and the output of a preliminary hydrological model, and simultaneously updating the parameters of each module through end-to-end backpropagation to obtain the runoff prediction amount. The runoff prediction method of the present invention fully captures the influences of dynamic changes such as precipitation and temperature, underlying surface distribution, and reservoir operation on basin runoff, and significantly improves the accuracy and stability of runoff simulation.

Description

Technical Field

[0001] The present invention belongs to the field of hydrological forecasting, and particularly relates to a method for predicting runoff by coupling hydrological system response and reservoir operation alternative network. Background Art

[0002] Hydrological forecasting and reservoir operation play crucial roles in water resources management and flood control and disaster reduction. Under the influence of climate change and human activities, there are uncertainties in climate elements and underlying surface characteristics, and the runoff simulation results often have errors. In addition, traditional hydrological models are difficult to quantify the impact of complex reservoir operations on the runoff formation process, reducing the accuracy of runoff forecasting. Therefore, comprehensively considering the superposition effect of hydrological system response and reservoir operation on runoff error is of great significance for improving runoff prediction accuracy and basin water management. With the development of machine learning models, data-driven methods can learn the complex nonlinear relationships of hydrological systems through large-scale historical data, correct runoff errors, and improve prediction accuracy. However, existing machine learning methods often only model the forecasting model or reservoir operation separately, failing to comprehensively consider the error sources of runoff forecasting and their propagation mechanisms, resulting in limited runoff prediction levels. Summary of the Invention

[0003] To solve the above technical problems, the present invention provides a runoff prediction method, device, and storage medium that effectively couple hydrological system response and reservoir operation alternative network.

[0004] To achieve the above object, the present invention specifically adopts the following technical solutions:

[0005] The present invention first provides a runoff prediction method, including the following steps:

[0006] Step S1, constructing a dynamic system response curve using meteorological inputs, and calculating the dynamic response characteristics of each moment and each grid cell, where the meteorological inputs include precipitation and temperature;

[0007] Step S2, extracting the static influence characteristics of runoff error from the underlying surface data of the basin through convolution and nonlinear transformation;

[0008] Step S3, using a neural network to align the dynamic response characteristics and static influence characteristics inputs, and extracting the characteristics that simultaneously reflect temporal and spatial influences to obtain the error correction amount generated based on meteorological inputs and underlying surface information;

[0009] Step S4, combining the reservoir operation status and scheduling requirements, constructing a reservoir operation alternative network, and outputting the correction component of reservoir operation on runoff;

[0010] Step S5: Collect runoff forecasts and measured data to construct a loss function. Superimpose the above correction components on the output of the preliminary hydrological model, and update the neural network model parameters simultaneously through end-to-end backpropagation to obtain the runoff prediction volume after error correction.

[0011] Runoff prediction volume: Attribute the sources of runoff error to the uncertainties of dynamic meteorological input data and static basin underlying surface data, as well as the impact of reservoir operation on runoff not being considered. The runoff prediction volume is equal to the sum of the simulated values of the hydrological model after restoring these three parts of errors. The uncertainty of meteorological data transmits errors through the dynamic system response curve, the uncertainty of the underlying surface data can provide static feature inputs for the neural network model, and reservoir operation serves as an alternative model output for the runoff correction component of the physical neural network.

[0012] In step S5, the specific algorithm for calculating the runoff prediction volume within the calculation period is as follows: In the formula, is the runoff prediction volume (m³ / s) after error correction within the period; is the simulated flow rate (m³ / s) of the original hydrological model during period ; is the error correction amount generated based on meteorological input and underlying surface information during period ; is the correction amount of the impact of reservoir operation on runoff during period . For the errors caused by meteorological input and underlying surface information, runoff generation is significantly affected by the lag effect of precipitation data, that is, the precipitation errors in the previous few periods will be transmitted to the current period's runoff error through the system response curve; at the same time, the underlying surface data provides characteristic inputs for each grid as a static attribute.

[0013] Therefore, is calculated as shown in formula (2). In the formula, is the dynamic and static element fusion module; is the dynamic response feature; is the basin static feature.

[0014] The specific method for convolving and fusing the dynamic response feature and the static feature is as follows: In the formula, is the output feature map; is the index of the output channel; is the activation function; is the period The concatenated feature vector in the grid ; is the input channel index, i.e., the total number after concatenating the dynamic and static feature inputs; and are the number of channels of the dynamic feature input data and the static feature input data, respectively; is the learnable weight of the 1×1 convolutional kernel in the channel dimension; is the bias of the convolutional kernel.

[0015] In step S3, the specific method for calculating the concatenated feature vector of the time period in the grid is as follows: In the formula, represents concatenating the feature data in the channel dimension.

[0016] In step S1, the specific calculation method for the dynamic response feature is as follows: In the formula, is the considered lag order, i.e., performing convolutional calculation on the data of the past time periods at the time period ; and are the precipitation and temperature of the time period at the grid scale, respectively; and are the weight coefficients of the precipitation and temperature data at the grid scale, respectively.

[0017] In step S2, the specific method for calculating the basin static feature is as follows: In the formula, is the static attribute of the grid , including soil type, vegetation type, and catchment area; represents a trainable neural network for extracting the influence of static attributes on runoff error.

[0018] In step S3, the specific method for calculating the error correction amount generated based on meteorological input and underlying surface information is as follows: In the formula, is the spatio-temporal correction weight, which can, to a certain extent, reflect the spatial heterogeneity, time lag effect, and the error propagation mechanism of the confluence process involved in the hydrological process within the basin as a parameter; is the output feature map, is the index of the output channel. The spatio-temporal correction weight is calculated as follows: In the formula, is the catchment area corresponding to this grid point.

[0019] In step S4, the specific algorithm for constructing the reservoir operation alternative network is as follows: In the formula, the input layer includes the reservoir water level during the time period, the reservoir inflow and the reservoir storage The reservoir storage is obtained by deriving from the water level-storage relationship curve; the output layer is through the water balance equation and the constraints of the outflow discharge and the water level limit.

[0020] In step S5, the specific method for calculating the loss function is as follows: In the formula, is the loss function (root mean square error); is the total number of time steps for calculating the error; is the observed runoff.

[0021] The present invention also provides a runoff prediction device, including a processor and a memory; the memory stores programs or instructions, and the programs or instructions are loaded and executed by the processor to implement the steps of the runoff prediction method.

[0022] The present invention also provides a computer-readable storage medium, on which programs or instructions are stored, and when the programs or instructions are executed by a processor, the steps of the runoff prediction method are implemented.

[0023] Advantages of the present invention: The present invention proposes a runoff prediction method that couples the response of the hydrological system and reservoir operation. First, a dynamic system response curve is constructed using meteorological inputs such as precipitation and temperature to calculate the dynamic response characteristics at each moment and each grid cell. Then, the influence characteristics of the static attributes of the basin underlying surface on runoff error are extracted through convolution and non-linear transformation. Next, a neural network is used to align the dynamic and static feature inputs to extract features that simultaneously reflect temporal and spatial influences and generate spatio-temporal correction weights. After that, considering the reservoir operation status and scheduling requirements, a reservoir operation substitution network is constructed to output the correction component of reservoir operation on runoff. Finally, a loss function is constructed by collecting runoff forecasts and measured data, and the above correction component is superimposed on the output of the preliminary hydrological model. The parameters of each module are updated simultaneously through end-to-end backpropagation to obtain the runoff prediction. The present invention proposes a runoff prediction method that couples the response of the hydrological system and reservoir operation substitution network, considering the superposition effects of dynamic system response, basin static attributes, and reservoir operation on runoff error, solving the problem that current runoff error correction methods are difficult to quantify various error sources and their propagation mechanisms, and can effectively improve the accuracy of hydrological forecasting. Description of the Drawings

[0024] Figure 1 is a schematic flow chart of the runoff prediction method that couples the response of the hydrological system and reservoir operation provided by the present invention;

[0025] Figure 2 is a distribution map of the dynamic response characteristics of the basin in a specific embodiment;

[0026] Figure 3 is a distribution map of the static characteristics of the basin in a specific embodiment;

[0027] Figure 4 is the process of the reservoir operation water level process line in the basin in a specific embodiment;

[0028] Figure 5 is the daily runoff correction result of the runoff prediction method that couples the response of the hydrological system and reservoir operation in a specific embodiment. Detailed Embodiments

[0029] The present invention will be further described below with reference to the drawings and specific embodiments.

[0030] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0031] Embodiment 1

[0032] As Figure 1 shown, the present invention provides a runoff prediction method that couples the response of the hydrological system and reservoir operation, including the following steps:

[0033] Step S1. Construct a dynamic system response curve using meteorological inputs such as precipitation and temperature, and calculate the dynamic response characteristics of each grid cell at each moment. The specific steps are as follows:

[0034] Step S101. Construct a dynamic system response curve using meteorological inputs such as precipitation and temperature;

[0035] Step S102. Calculate the dynamic response characteristics of each grid cell at each moment: where, is the dynamic response characteristic of grid during time period ; and are the weight coefficients of precipitation and temperature data at lag days of at the grid scale, respectively; is the considered lag order, that is, convolution calculation is performed on the data of the past time periods during time period ; and are the precipitation and temperature of grid at lag days of , respectively.

[0036] Obtain the precipitation and temperature grid data of the Jin'anqiao Basin in the middle reaches of the Jinsha River Basin from 2013 to 2020. Take each grid cell of the meteorological data as a calculation unit, construct the system response relationship between the runoff error component and the meteorological input error, and calculate the dynamic response characteristics of each grid cell using convolution transformation, as shown in Figure 2 .

[0037] Step S2. Extract the static influence characteristics of the static attributes of the basin underlying surface on the runoff error through convolution and non-linear transformation. The specific steps are as follows:

[0038] Step S201. Extract the static attributes of the basin, such as soil type, vegetation type, and catchment area;

[0039] Step S202. Map the static attributes of the basin to the influence characteristic space of the runoff error through convolution and non-linear transformation to obtain the static characteristics of the basin: where, is the static characteristic of the basin of grid ; is the static attribute of grid ; represents a trainable neural network for extracting the static characteristics of the basin that reflect the influence of static attributes on the runoff error. is a known network, and the network output is the encoded soil-vegetation-catchment area composite attribute vector, that is, the static feature .

[0040] Download soil type and vegetation type data, use GIS spatial analysis tools to obtain the static attributes of the Jinanqiao watershed, and map the static attributes of the Jinanqiao watershed to the influencing feature space of runoff error through convolution and nonlinear transformation, such as Figure 3 shown.

[0041] Step S3, using a neural network to align the dynamic feature and static feature inputs, extracting features that simultaneously reflect the effects of time and space, and obtaining error correction amounts based on meteorological input and underlying surface information.

[0042] Step S301, using a neural network to perform data alignment on dynamic feature and static feature inputs: In the formula, is the concatenated feature vector after alignment and concatenation, , It means that the concatenated feature map is a spatial size of , the number of channels is A three-dimensional tensor of ; is the input channel index, i.e. the total number of dynamic and static feature inputs after concatenation; Indicates concatenation of feature data in the channel dimension; and are the number of channels for dynamic feature input data and static feature input data respectively; is the vertical number of the grid, is the horizontal number of the grid.

[0043] Step S302, using convolution to fuse dynamic and static features, to obtain features that can simultaneously reflect the effects of time and space: In the formula, is the output feature map; is the index of the output channel; is the activation function; is the learnable weight of the 1×1 convolution kernel in the channel dimension; is the bias of the convolution kernel.

[0044] Step S303, defining the spatiotemporal correction weights, and calculating the error correction amount generated based on the meteorological input and the underlying surface information;

[0045] Among them, the spatiotemporal correction weight is defined as: In the formula, is the spatio-temporal correction weight, which reflects the spatial heterogeneity involved in the hydrological process within the basin through the catchment area of each grid cell and the propagation and contribution of the confluence process to the error; the catchment area corresponding to this grid point;

[0046] Based on the defined spatio-temporal correction weight , calculate the error correction component generated by meteorological input and underlying surface information: In the formula, is the error correction component generated by meteorological input and underlying surface information.

[0047] According to the proportion of the confluence area of each grid cell in the Jin'anqiao Basin, determine the spatio-temporal correction weight of each grid cell, and calculate the error correction component generated by meteorological input and underlying surface information.

[0048] Step S4, combine the reservoir operation status and scheduling requirements, construct a reservoir scheduling alternative network, and output the correction component of the reservoir scheduling to the runoff.

[0049] Step S401, construct a water balance equation to quantify the reservoir operation status and scheduling requirements: In the formula, is the inflow during period ; is the outflow during period ; is the reservoir storage during period , obtained through the water level-storage relationship; is the reservoir water level during period , is the functional relationship between the water level and the storage, used to calculate the reservoir storage corresponding to this water level; Equations (9) and (10) are the outflow constraint and the water level limit constraint respectively.

[0050] Step S402, combine the reservoir operation status and scheduling requirements, construct a reservoir scheduling alternative network, and output the correction component of the reservoir scheduling to the runoff: In the formula, is the reservoir scheduling alternative model constructed based on the neural network, is the trainable parameter; is the output layer, that is, the correction component of the reservoir scheduling to the runoff, and the outflow range is restricted through the activation function: In the formula, The weights of the first layer, the second layer, and the output layer of the reservoir surrogate network, respectively; The biases of the corresponding reservoir surrogate network; is the activation function of the reservoir surrogate network; and are intermediate hidden layer variables, representing the output results of the neurons in the first layer and the second layer, respectively.

[0051] Combined with the operation status and scheduling requirements of Liyuan Reservoir, the downstream water level process line of Liyuan Reservoir in the upper reaches of Jin'anqiao Basin is obtained, as Figure 4 shown.

[0052] Step S5, collect runoff forecast and measured data to construct a loss function, superimpose the above correction components and the output of the preliminary hydrological model, and update the parameters of each module simultaneously through end-to-end backpropagation to obtain the runoff prediction.

[0053] Step S501, collect runoff forecast and measured data to construct a loss function: In the formula, is the loss function (mean square error); is the total number of time steps for calculating the error; Observed runoff (m³ / s); is the runoff prediction after error correction within the time period.

[0054] Step S502, superimpose the system response correction component and the reservoir operation correction component with the output of the preliminary hydrological model, and update the network model parameters simultaneously through end-to-end backpropagation to obtain the runoff prediction: In the formula, is the runoff prediction after error correction within the time period; is the time period The simulated flow of the original hydrological model under; Time period The error correction amount generated based on meteorological input and underlying surface information under; is the time period The correction amount of the impact of reservoir operation on runoff under.

[0055] Taking 2014 - 2019 as the calibration period, 2020 - 2022 as the verification period, and 2023 - 2024 as the test period, the effect of the corrected runoff volume in the Jin'anqiao Basin is as Figure 5As shown in the figure. According to Step 1, the dynamic response characteristics of each moment and each grid cell in the Jin'anqiao Basin are calculated using precipitation and temperature. Then, the influence characteristics of the extracted underlying surface information of the basin on the runoff error are analyzed. Next, the dynamic and static data are fused to extract the characteristics that reflect both temporal and spatial influences, and the spatio-temporal correction weights are generated. Then, considering the operation status and scheduling requirements of the Liyuan Hydropower Station Reservoir in the upper reaches of the Jin'anqiao Basin, a reservoir scheduling alternative network is constructed, and the correction component of the reservoir scheduling on the runoff is output. Finally, a loss function is constructed using the mean square error, and the neural network is trained to obtain the runoff prediction. The average relative error is used as the error correction evaluation index, and its formula is: In the formula, is the total number of time steps for calculating the error; is the observed runoff (m³ / s); is the runoff prediction after error correction within the time period.

[0056] During the calibration period, is 6.4%, and during the verification period, is 7.2%. During the test period is 4.8%, indicating that the runoff prediction method that couples the hydrological system response and the reservoir scheduling alternative network has a good simulation effect on the runoff in the Jin'anqiao Basin.

[0057] This embodiment provides a runoff prediction device, including a processor and a memory; a program or instruction is stored in the memory, and the program or instruction is loaded and executed by the processor to implement the steps of the runoff prediction method in the above embodiment.

[0058] This embodiment provides a computer-readable storage medium, and a program or instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, the steps of the runoff prediction method in the above embodiment are implemented.

[0059] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art should consider the scope of the present invention to be protected if they make several improvements and optimizations without departing from the concept of the present invention.

Claims

1. A runoff prediction method, characterized in that, The following steps are involved: Step S1, constructing a dynamic system response curve using meteorological input to deduce the dynamic response characteristics of each grid unit at each time, wherein the meteorological input includes precipitation and temperature; Step S2, extracting static influence characteristics of static attributes on runoff error from the watershed underlying surface data through convolution and nonlinear transformation; Step S3, using a neural network to align the dynamic response characteristics and static impact characteristics input, extracting the characteristics that reflect both time and space impacts, and obtaining the error correction amount generated based on the meteorological input and the underlying surface information; Step S4, combining the reservoir operation status and dispatching requirements, constructing a reservoir dispatching alternative network, and outputting the correction component of reservoir dispatching on runoff; Step S5, collecting runoff forecast and measured data to construct a loss function, superimposing the above correction component with the output of the preliminary hydrological model, and simultaneously updating the neural network model parameters through end-to-end back propagation to obtain the runoff prediction after error correction; Step S3 includes: Step S301: Align the input of dynamic features and static features using a neural network: In the formula, is the concatenated feature vector after alignment and concatenation, , indicates that the concatenated feature map is a three-dimensional tensor with a spatial size of and a number of channels of ; is the input channel index, i.e., the total number after concatenating the dynamic and static feature inputs; indicates concatenating the feature data in the channel dimension; and are the numbers of channels of the dynamic feature input data and the static feature input data, respectively; is the longitudinal number of the grid, is the transverse number of the grid; is the dynamic response feature of the grid at time period ; is the basin static feature of the grid . Step S302: Use convolution to fuse dynamic and static features to obtain features that can simultaneously reflect the influence of time and space: In the formula, is the output feature map; is the index of the output channel; is the activation function; is the learnable weight of the 1×1 convolution kernel in the channel dimension; is the bias of the convolution kernel; Step S303, defining the spatiotemporal correction weights, and calculating the error correction amount generated based on the meteorological input and the underlying surface information; Among them, the spatio-temporal correction weight is defined as: In the formula, is the spatio-temporal correction weight, which reflects the spatial heterogeneity involved in the hydrological process within the basin through the catchment area of each grid cell and the propagation and contribution of the confluence process to the error; is the catchment area corresponding to this grid point; Spatiotemporal correction weights based on definitions , calculate the error correction component generated by meteorological input and underlying surface information: In the formula, is the error correction component generated by meteorological input and underlying surface information.

2. The runoff prediction method according to claim 1, wherein Dynamic response characteristics are as follows: In the formula, is the considered lag order, that is, in the time period convolution calculation is performed on the data of the past time periods; and are the precipitation and temperature of grid when the lag days are respectively; and are the weight coefficients of precipitation and temperature data at the grid scale respectively.

3. The runoff prediction method according to claim 2, wherein Static characteristics of the basin are as follows: In the formula, is the static attribute of grid , including soil type, vegetation type and catchment area; represents a trainable neural network for outputting the encoded composite attribute vector of soil-vegetation-catchment area.

4. The runoff prediction method according to claim 2, characterized in that, Step S4 includes: Step S401: Construct a water balance equation to quantify the reservoir operation status and scheduling requirements: In the formula, is the inflow during time period ; is the outflow during time period ; is the reservoir storage during time period , which is obtained through the water level - storage relationship; is the reservoir water level at time period , is the functional relationship between the water level and the storage, which is used to calculate the reservoir storage corresponding to this water level; and are the minimum and maximum values of the outflow , respectively; and are the minimum and maximum values of the reservoir water level , respectively. Step S402: Combine the reservoir operation status and the scheduling requirements to construct a reservoir scheduling alternative network, and output the correction component of the reservoir scheduling for runoff: In the formula, is a reservoir scheduling alternative model constructed based on a neural network, are trainable parameters; is the correction component of the reservoir scheduling for runoff.

5. The runoff prediction method according to claim 4, characterized in that Limit the outbound range through the activation function: In the formula, and are intermediate hidden layer variables, representing the output results of the first and second layers of the reservoir substitution network respectively; are the weights of the first layer, second layer and output layer of the reservoir substitution network respectively; are the biases of the corresponding reservoir substitution network; is the activation function of the reservoir substitution network.

6. The runoff prediction method according to claim 4, wherein Step S5 includes: Step S501, collecting runoff forecast and measured data to construct a loss function; Step S502: Superimpose the system response correction component and the reservoir operation correction component on the output of the preliminary hydrological model, and simultaneously update the neural network model parameters through end-to-end backpropagation to obtain the runoff prediction: In the formula, is the runoff prediction after error correction within the time period; is the time period The simulated flow of the original hydrological model under; is the time period The error correction amount generated based on meteorological input and underlying surface information under; is the time period The correction amount of the influence of reservoir operation on runoff under.

7. The runoff prediction method according to claim 6, wherein In step S501, the constructed loss function is as follows: In the formula, is the loss function; is the total number of time steps for calculating the error; is the observed runoff; is the runoff prediction after error correction within the time period.

8. A runoff prediction device, characterized in that, It comprises a processor and a memory; the memory stores a program or instruction, and the program or instruction is loaded and executed by the processor to implement the steps of the runoff prediction method as claimed in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the runoff prediction method according to any one of claims 1 to 7 are implemented.

Images