A method, device, equipment and medium for determining a watershed ecological water supplement mode

Abstract

The present application relates to the technical field of watershed ecological water supplement, and discloses a method, device, equipment and medium for determining a watershed ecological water supplement mode, which comprises the following steps: obtaining measured data of a target watershed ecological water supplement process; simulating the ecological water supplement process to obtain simulation data of water supplement effect corresponding to a water supplement execution process under different water supplement modes; training a preset machine learning model with combined data of the measured data and the simulation data, so as to construct a nonlinear mapping relationship between input data and output data; constructing a table list corresponding to the water supplement execution process and the water supplement effect of the target watershed ecological water supplement process under different water supplement modes based on the nonlinear mapping relationship, and determining the ecological water supplement mode of the target watershed based on the table list. The present application extracts ecological water supplement modes with different target effect constraints, provides a basis for water resource allocation and scheduling schemes under different water supplement target effects, and can quickly formulate ecological schemes to guide watershed ecological water supplement operations.

Description

Technical Field

[0001] This invention relates to the field of watershed ecological water replenishment technology, specifically to a method, apparatus, equipment, and medium for determining a watershed ecological water replenishment mode. Background Technology

[0002] Watershed ecological water replenishment refers to the supply of water resources to ecosystems in arid or semi-arid regions through artificial or natural means to restore or maintain the hydrological and ecological functions of the ecosystems. The main purpose of ecological water replenishment is to maintain or improve the hydrological and ecological processes of the ecosystems, maintain and enhance the biodiversity and ecosystem service functions of the ecosystems, and promote regional sustainable development.

[0003] Currently, many cities in China are actively promoting ecological water replenishment, which involves introducing water sources to increase river flow, improve water quality, enhance the river's ecological environment, and improve urban water quality and ecosystem service capacity. However, there is limited research on methods and models for ecological water replenishment at present. Replenishment relies heavily on the experience and practices of local water authorities to determine specific replenishment volumes, flows, models, and processes. This leads to insufficient estimation of the actual effects and benefits of ecological water replenishment, and the resulting water resource allocation and scheduling plans often fail to achieve optimal targets. Summary of the Invention

[0004] In view of this, in order to address the shortcomings of existing watershed ecological water replenishment schemes, which are ineffective and fail to achieve the desired water replenishment effect, this invention provides a method, apparatus, equipment, and medium for determining watershed ecological water replenishment patterns.

[0005] In a first aspect, the present invention provides a method for determining a watershed ecological water replenishment pattern, comprising:

[0006] Obtain measured data on the ecological water replenishment process in the target watershed;

[0007] The ecological water replenishment process was simulated using a pre-set water replenishment model to obtain simulation data of the water replenishment effect corresponding to the water replenishment execution process under different water replenishment modes.

[0008] The combined data of water replenishment execution process data under different water replenishment modes in the measured data and simulation data are used as input data, and the combined data of water replenishment effect data in the measured data and simulation data are used as output data to train a preset machine learning model to construct a nonlinear mapping relationship between input data and output data.

[0009] Based on the nonlinear mapping relationship between input and output data, a table list is constructed showing the water replenishment process and effects under different water replenishment modes for the target watershed. Based on the table list, the ecological water replenishment mode for the target watershed is determined.

[0010] The method for determining the watershed ecological water replenishment model provided in this embodiment provides a basis for water resource allocation and scheduling schemes under different water replenishment target effects by refining ecological water replenishment models with different target effect constraints. It can quickly formulate ecological schemes to guide ecological water replenishment operations.

[0011] In one optional implementation, the parameter data involved in the water replenishment execution process under different water replenishment modes include: total water replenishment, discharge form, discharge process, and outflow water level.

[0012] In one optional implementation, the discharge form includes: square wave, triangular wave, matrix wave, and constant flow discharge, and the discharge process includes: start-up time, start-up flow rate, peak duration, peak interval time, peak flow rate, and water replenishment end time.

[0013] The embodiments of the present invention, by analyzing the parameter data related to the water replenishment process and effects under different water replenishment modes from various dimensions, can meet the desired water replenishment effect under different operational constraints.

[0014] In one optional implementation, the parameters involved in the water replenishment effect include: cross-sectional water absorption rate, head evolution time, water loss, channel storage capacity, water surface area, and outflow volume.

[0015] This invention, by setting parameters related to the water replenishment effect, can comprehensively evaluate the entire process of ecological water replenishment, surface water recovery, and groundwater recharge, and can more accurately meet the water replenishment effect under different constraint parameters.

[0016] In one alternative implementation, the preset machine learning model is an LSTM model.

[0017] Because the LSTM model performs exceptionally well in time series prediction, this embodiment of the invention uses LSTM as the data training model. The LSTM model is a special type of recurrent neural network, and its long short-term memory structure is designed to overcome the gradient vanishing and gradient explosion problems in RNNs.

[0018] In one optional implementation, determining the ecological water replenishment pattern for the target watershed based on the table list includes:

[0019] By searching through a table list, we can obtain the water replenishment effect corresponding to the parameter data used in the water replenishment process under different water replenishment modes, or calculate the set of operational parameters included in the corresponding ecological water replenishment process based on the target water replenishment effect, which can be used to assist in the selection of ecological water replenishment operation modes and corresponding parameters.

[0020] This invention provides technical support for quickly generating ecological solutions and guiding ecological water replenishment operations by searching a table list.

[0021] In one optional implementation, the target water replenishment effect includes: river and lake recovery effect, groundwater conservation effect, and water replenishment execution effect; wherein, the river and lake recovery effect is determined by water surface area, channel storage capacity, and other derivative quantities; the groundwater conservation effect is determined by water loss and other derivative quantities; and the water replenishment execution effect is determined by cross-sectional water intake rate, head evolution time, outflow volume, and other derivative quantities.

[0022] The operating parameters include: water volume control parameters, water level control parameters, and process control parameters; among which: the water volume control parameter is the total amount of water replenished, the water level control parameter is the outflow water level, and the process control parameters include: start-up time, start-up flow rate, flood peak duration, flood peak interval time, and flood peak flow rate.

[0023] By mapping different water replenishment effect parameters to target effects, this invention provides a basis for water resource allocation and scheduling schemes under different water replenishment targets and constraints.

[0024] Secondly, the present invention provides a device for determining a watershed ecological water replenishment pattern, the device comprising:

[0025] The ecological water replenishment measured data acquisition module is used to acquire measured data of the ecological water replenishment process in the target watershed;

[0026] The ecological water replenishment simulation data acquisition module is used to simulate the ecological water replenishment process using a preset water replenishment model, and obtain simulation data of the water replenishment effect corresponding to the water replenishment execution process under different water replenishment modes.

[0027] The model training module is used to take the combined data of water replenishment execution process data under different water replenishment modes in the measured data and simulation data as input data, and the combined data of water replenishment effect data in the measured data and simulation data as output data to train a preset machine learning model, so as to build a non-linear mapping relationship between input data and output data.

[0028] An ecological water replenishment mode determination module is used to construct a table list of the water replenishment execution process and water replenishment effect of the target watershed under different water replenishment modes based on the nonlinear mapping relationship between input data and output data, and to determine the ecological water replenishment mode of the target watershed based on the table list.

[0029] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for determining the watershed ecological water replenishment mode of the first aspect or any corresponding embodiment described above.

[0030] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for determining the watershed ecological water replenishment mode of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0031] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 This is a flowchart illustrating the method for determining the watershed ecological water replenishment mode provided in an embodiment of the present invention.

[0033] Figure 2 This is a schematic diagram of training an LSTM model based on input and output data provided in an embodiment of the present invention;

[0034] Figure 3 This is a structural block diagram of the device for determining the watershed ecological water replenishment mode provided in an embodiment of the present invention;

[0035] Figure 4 This is a schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Most existing ecological water replenishment models are based on practical experience. They do not fully estimate the actual implementation effects and benefits, such as the accuracy of water head arrival, water balance, river and lake recovery, and groundwater conservation. The water resource allocation and scheduling plans formulated often fail to achieve the optimal target state. That is, questions such as how to replenish water the fastest, or how to replenish water the most fully, or how to achieve the best river and lake recovery effect are difficult to solve and answer.

[0038] Based on this embodiment of the invention, an embodiment of a method for determining a watershed ecological water replenishment pattern is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer device such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0039] This embodiment provides a method for determining a watershed ecological water replenishment pattern, which can be used on a computer device terminal. Figure 1 This is a flowchart of a method for determining a watershed ecological water replenishment pattern according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0040] Step S101: Obtain measured data on the ecological water replenishment process of the target watershed.

[0041] In this embodiment of the invention, the ecological water replenishment process of the Yongding River, Chaobai River and Beiyun River basins in Beijing is collected and studied as an example. The measured data obtained include: average and peak water replenishment flow, total water replenishment, water replenishment time and form (constant flow, triangular wave or square wave water replenishment), water replenishment execution process (water head evolution time, outflow water volume, water collection rate), river and lake recovery effect (river length with water, water surface area and duration with water), and groundwater conservation (water loss) effect, etc.

[0042] Step S102: The ecological water replenishment process is simulated using a preset water replenishment model to obtain simulation data of the water replenishment effect corresponding to the water replenishment execution process under different water replenishment modes.

[0043] Specifically, since measured data on ecological water replenishment processes are often limited, this embodiment of the invention uses hydrological or hydrodynamic mathematical models to simulate and model the ecological water replenishment process based on the same water replenishment mode and execution process data as the measured data. This allows for the acquisition of the water replenishment execution process and effects under different water replenishment modes. The hydrological or hydrodynamic mathematical models used are reliable models verified by measured data. The parameters involved in the water replenishment execution process under different water replenishment modes include: total water replenishment volume, discharge form, discharge process, and outflow water level. Discharge forms include: square wave, triangular wave, matrix wave, and constant flow discharge. The discharge process includes: start-up time, start-up flow rate, peak duration, peak interval time, peak flow rate, and water replenishment end time.

[0044] In this embodiment of the invention, the parameters involved in the water replenishment effect include: cross-sectional water intake rate, head evolution time, water loss, channel storage capacity, water surface area, and outflow volume. The effects of river and lake recovery, groundwater conservation, head evolution process, and water balance are evaluated based on these parameters. Specifically, the cross-sectional water intake rate can be calculated by combining the cumulative water volume of the river cross-section with the replenishment volume; the head evolution time generally refers to the time required for the water head to reach a typical cross-section; water loss mainly considers surface evaporation and seepage losses; channel storage capacity refers to the channel storage capacity of the replenishing river, calculated by hydrological or hydrodynamic models based on river topographic data and cross-sectional water depth; the water surface area is generally obtained by integrating the river length with water and the river cross-sectional width; and the outflow volume is statistically calculated based on the local flow rate as a percentage of the cumulative value.

[0045] Step S103: The combined data of water replenishment execution process data under different water replenishment modes in the measured data and simulation data are used as input data, and the combined data of water replenishment effect data in the measured data and simulation data are used as output data to train the preset machine learning model to build a nonlinear mapping relationship between the input data and the output data.

[0046] Because the LSTM model performs exceptionally well in time series prediction, this embodiment of the invention uses LSTM as the data training model. LSTM was originally proposed as a special type of recurrent neural network, and its long short-term memory structure is designed to overcome the gradient vanishing and gradient exploding problems in RNNs.

[0047] The LSTM model is controlled and protected by three gates: the input gate, the forget gate, and the output gate. The information flow in the LSTM model can be described in three steps: First, the information to be discarded from the cell state is determined. This decision is made through the forget gate. The gate reads h... t-1 x t Each cell state outputs a value C between 0 and 1. t-1 , where 1 means "keep completely" and 0 means "discard completely".

[0048] F t =σ(W f g[h t-1 ,x t ]+b f )

[0049] The next step is to determine how much new information should be added to the cell state. This requires two steps: First, a Sigmoid layer, called the "input gate layer," determines which information should be retained; the tanh layer generates a vector containing the optional content to be retained, C. t In the next step, link these two parts to preserve the state of the cell.

[0050] I t =σ(W i ·g[h t-1 ,x t ]+b i )

[0051]

[0052]

[0053] Finally, the output value needs to be determined. This output will be based on the cell state, but it is also a filtered result. The Sgmoid layer determines which part of the cell state will be output. Next, we process the cell state using tanh (to obtain a value between -1 and 1) and multiply it by the output of the Sgmoid layer, ultimately only outputting the determined portion.

[0054] O t =σ(W o ·[h t-1 ,x t ]+b o )

[0055] h t =O t *tanh(C t )

[0056] Where, F t Represents the Gate of Oblivion; I t Represents the input gate; This is another candidate gate created using the tanh function, used to calculate the cell state of the current input; C t Indicates the update status of the new cell; O t Indicates the output gate; h t This represents the final output calculated by the tanh function; σ represents the Sgmoid function; h t-1 Indicates the output of the previous unit; xt Represents the current cell input; tanh represents the hyperbolic cosine function; W f W i W c and W o These represent the weight parameter matrices between the hidden layer forget gate, input gate, candidate gate, and output gate and the neurons in the previous layer at the current time step; b f b i b c and b o These represent the deviations of the forget gate, input gate, candidate part, and output gate, respectively.

[0057] This invention uses a combination of measured and simulated data on the water replenishment process under different replenishment modes as input data (for example, using 20 sets from the measured data and 100 sets from the simulated data; if 3 sets from the measured data and 3 sets from the simulated data correspond repeatedly, then 20-3+100 sets of data are actually used as training input data). The combined data of measured data and simulated data on the water replenishment effect is used as output data. Specifically, for example... Figure 2 As shown, the input parameter of the LSTM model is the total water replenishment Q. i , starting flow rate q 0i , start time t 0i Peak flow rate q pi Flood peak duration t pi Flood peak interval t si and outbound water level L i Let i be a water source upstream; the output parameters are cross-sectional water recovery rate s, evolution time T, water loss S, channel storage capacity W, water surface area M, and outflow water volume Q. oi .

[0058] In other embodiments, the LSTM model described above can also be replaced with a recurrent neural network (RNN), backpropagation (BP), or RBF neural network.

[0059] Step S104: Based on the nonlinear mapping relationship between input data and output data, construct a table list of the water replenishment process and water replenishment effect of the target watershed ecological water replenishment process under different water replenishment modes, and determine the ecological water replenishment mode of the target watershed based on the table list.

[0060] Specifically, the water replenishment effect corresponding to the parameter data used in the water replenishment process under different water replenishment modes can be obtained by looking up the table list, or the set of operation parameters included in the corresponding ecological water replenishment process can be calculated based on the target water replenishment effect, which can be used to assist in the selection of ecological water replenishment operation mode and corresponding parameters, forming the scheme parameter list shown in Table 1 below.

[0061] Table 1

[0062]

[0063] This embodiment also provides a device for determining a watershed ecological water replenishment pattern. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0064] This embodiment provides a device for determining a watershed ecological water replenishment pattern, such as... Figure 3 As shown, it includes:

[0065] The ecological water replenishment measured data acquisition module 301 is used to acquire measured data of the ecological water replenishment process in the target watershed;

[0066] The ecological water replenishment simulation data acquisition module 302 is used to simulate the ecological water replenishment process using a preset water replenishment model, and obtain simulation data of the water replenishment effect corresponding to the water replenishment execution process under different water replenishment modes.

[0067] The model training module 303 is used to take the combined data of water replenishment execution process data under different water replenishment modes in the measured data and simulation data as input data, and the combined data of water replenishment effect data in the measured data and simulation data as output data to train the preset machine learning model, so as to build a non-linear mapping relationship between the input data and the output data.

[0068] The ecological water replenishment mode determination module 304 is used to construct a table list of the water replenishment execution process and water replenishment effect of the target watershed under different water replenishment modes based on the nonlinear mapping relationship between input data and output data, and to determine the ecological water replenishment mode of the target watershed based on the table list.

[0069] In one optional implementation, the parameter data involved in the water replenishment execution process under different water replenishment modes in the ecological water replenishment simulation data acquisition module includes: total water replenishment, discharge form, discharge process, and outflow water level. Discharge forms include: square wave, triangular wave, matrix wave, and constant flow discharge. The discharge process includes: start-up time, start-up flow rate, peak duration, peak interval time, peak flow rate, and water replenishment end time. Parameter data related to the water replenishment effect include: cross-sectional water intake rate, head evolution time, water loss, channel storage capacity, water surface area, and outflow water volume.

[0070] In one optional implementation, the preset machine learning model in the model training module is an LSTM model.

[0071] In one optional implementation, the ecological water replenishment mode determination module obtains the water replenishment effect corresponding to the parameter data used in the water replenishment execution process under different water replenishment modes by looking up a table list, or calculates the set of operation parameters included in the corresponding ecological water replenishment execution process based on the target water replenishment effect, in order to assist in the selection of ecological water replenishment operation mode and corresponding parameters.

[0072] In one optional implementation, the target water replenishment effect includes: river and lake recovery effect, groundwater conservation effect, and water replenishment execution effect; wherein, the river and lake recovery effect is determined by water surface area, channel storage capacity, and other derivative quantities; the groundwater conservation effect is determined by water loss and other derivative quantities; and the water replenishment execution effect is determined by cross-sectional water intake rate, water head evolution time, outflow volume, and other derivative quantities.

[0073] The operating parameters include: water volume control parameters, water level control parameters, and process control parameters; among which: the water volume control parameter is the total amount of water replenished, the water level control parameter is the outflow water level, and the process control parameters include: start-up time, start-up flow rate, flood peak duration, flood peak interval time, and flood peak flow rate.

[0074] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0075] This invention also provides a computer device having the above-described features. Figure 3 The apparatus shown is for determining the watershed ecological water replenishment model.

[0076] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor device). Figure 4 Take a processor 10 as an example.

[0077] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0078] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0079] The memory 20 may include a program storage area and a data storage area. The program storage area may store applications required for operating the device and at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0080] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0081] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0082] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0083] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for determining a watershed ecological water replenishment model, characterized in that, include: Obtain measured data on the ecological water replenishment process in the target watershed; The ecological water replenishment process was simulated using a pre-set water replenishment model to obtain simulation data of the water replenishment effect corresponding to the water replenishment execution process under different water replenishment modes. The combined data of water replenishment execution process data under different water replenishment modes in the measured data and simulation data are used as input data, and the combined data of water replenishment effect data in the measured data and simulation data are used as output data to train a preset machine learning model to construct a nonlinear mapping relationship between input data and output data. The water replenishment effect data includes: cross-sectional water absorption rate, head evolution time, water loss, channel storage capacity, water surface area, and outflow volume; the preset machine learning model is an LSTM model; Based on the nonlinear mapping relationship between input and output data, a table list is constructed showing the water replenishment process and effects under different water replenishment modes for the target watershed. Based on the table list, the ecological water replenishment mode for the target watershed is determined.

2. The method according to claim 1, characterized in that, The parameters involved in the water replenishment process under the different water replenishment modes include: total water replenishment, discharge method, discharge process, and outflow water level.

3. The method according to claim 2, characterized in that, The discharge forms include: square wave, triangular wave, matrix wave and constant flow discharge, and the discharge process includes: start-up time, start-up flow, peak duration, peak interval time, peak flow and water replenishment end time.

4. The method according to claim 1, characterized in that, The process of determining the ecological water replenishment pattern for the target watershed based on the table list includes: By searching through a table list, we can obtain the water replenishment effect corresponding to the parameter data used in the water replenishment process under different water replenishment modes, or calculate the set of operational parameters included in the corresponding ecological water replenishment process based on the target water replenishment effect, which can be used to assist in the selection of ecological water replenishment operation modes and corresponding parameters.

5. The method according to claim 4, characterized in that, The target water replenishment effect includes: river and lake recovery effect, groundwater conservation effect, and water replenishment execution effect; wherein, the river and lake recovery effect is determined by water surface area, channel storage capacity, and other derivative quantities; the groundwater conservation effect is determined by water loss and other derivative quantities; and the water replenishment execution effect is determined by cross-sectional water intake rate, water head evolution time, outflow volume, and other derivative quantities. The operating parameters include: water volume control parameters, water level control parameters, and process control parameters; among which: The water volume control parameter is the total amount of water replenished, the water level control parameter is the outflow water level, and the process control parameters include: start-up time, start-up flow rate, peak duration, peak interval time, and peak flow rate.

6. A device for determining a watershed ecological water replenishment pattern, characterized in that, include: The ecological water replenishment measured data acquisition module is used to acquire measured data of the ecological water replenishment process in the target watershed; The ecological water replenishment simulation data acquisition module is used to simulate the ecological water replenishment process using a preset water replenishment model, and obtain simulation data of the water replenishment effect corresponding to the water replenishment execution process under different water replenishment modes. The model training module is used to take the combined data of water replenishment execution process data under different water replenishment modes in the measured data and simulation data as input data, and the combined data of water replenishment effect data in the measured data and simulation data as output data to train a preset machine learning model, so as to build a non-linear mapping relationship between input data and output data. The water replenishment effect data includes: cross-sectional water absorption rate, head evolution time, water loss, channel storage capacity, water surface area, and outflow volume; the preset machine learning model is an LSTM model; An ecological water replenishment mode determination module is used to construct a table list of the water replenishment execution process and water replenishment effect of the target watershed under different water replenishment modes based on the nonlinear mapping relationship between input data and output data, and to determine the ecological water replenishment mode of the target watershed based on the table list.

7. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the method for determining the watershed ecological water replenishment mode according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the method for determining the watershed ecological water replenishment mode according to any one of claims 1 to 5.

Images