Irrigation canal water transfer optimization method and system, terminal and storage medium

Abstract

The invention relates to the technical field of data processing, and particularly provides an irrigation canal water transfer optimization method and system, a terminal and a storage medium, and the method comprises the steps: collecting meteorological data, and predicting the flow of a main canal based on the meteorological data through a pre-trained prediction model; land parcel information corresponding to the branch canal is obtained, the land parcel information comprises crop types, areas and land parcel humidity, and irrigation requirements of the branch canal are generated based on the land parcel information; constructing a water distribution model based on the predicted value of the main canal flow and the irrigation demand of each branch canal; and solving the water distribution model to obtain an optimal water transfer scheme. According to the method, the irrigation requirements of the branch canals and the actual flow of the main canal are considered, the number of the rotation irrigation groups and the water diversion branch canals contained in the rotation irrigation groups are scientifically formulated, water resources are reasonably utilized, and the irrigation time is also saved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to an irrigation channel water diversion optimization method, system, terminal and storage medium. Background Art

[0002] In the currently widely used irrigation system, rotation irrigation is widely adopted as a common irrigation strategy. However, this rotation irrigation allocation mechanism is largely arbitrary and extensive. Specifically, it often simply sets exactly the same water distribution time for each group of rotation irrigation branches, without carefully considering key factors such as crop types, soil conditions, growth cycles, and historical water consumption in different regions. The fundamental flaw of this "one-size-fits-all" management method is that it ignores the actual differences in irrigation demand between different branches, thus failing to achieve accurate allocation of irrigation resources.

[0003] Due to the lack of scientific basis and support for refined management, the existing rotation irrigation plan is particularly unreasonable in the formulation process. It neither fully considers the dynamic changes in crop growth's demand for water, nor effectively responds to differences in soil moisture retention capacity, nor fully utilizes advanced water resource management technologies to optimize irrigation strategies. This extensive management model directly leads to uneven irrigation. Some areas may cause root diseases or nutrient loss due to excess water, while other areas may limit the normal growth and development of crops due to water shortage, seriously affecting the yield and quality of crops.

[0004] What is more serious is that this unreasonable irrigation scheme has also exacerbated the problem of water waste. When the water distribution time is the same but the actual demand is different, a lot of water resources are wasted in areas that do not need or are over-irrigated. This not only increases the cost of agricultural production, but also puts additional pressure on the already tight water resource reserves, which is not conducive to the sustainable development of agriculture and the protection of the ecological environment. Therefore, reforming and improving the current irrigation system and realizing refined rotation irrigation management based on actual needs and efficient use of water resources has become an important issue that needs to be solved urgently. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides an irrigation channel water diversion optimization method, system, terminal and storage medium to solve the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides an irrigation canal water diversion optimization method, comprising: Collecting meteorological data and predicting the flow of the main channel based on the meteorological data using a pre-trained prediction model; Acquire the plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generate the irrigation demand of the branch canal based on the plot information; Construct a water distribution model based on the predicted value of the main canal flow and the irrigation demand of each branch canal; The water distribution model is solved to obtain the optimal water diversion plan.

[0007] In an optional embodiment, collecting meteorological data and using a pre-trained prediction model to predict the main channel flow based on the meteorological data includes: Collecting meteorological data, including temperature, humidity, and precipitation; Acquiring weather forecast data, wherein the weather forecast data includes predicted temperature, predicted humidity and predicted precipitation; Integrate meteorological data and meteorological forecast data into meteorological data series; The meteorological data sequence is input into a pre-trained long short-term memory neural network model to obtain the flow prediction value of the main channel in the future period.

[0008] In an optional implementation, the meteorological data and the meteorological forecast data are integrated into a meteorological data sequence, including: Sort the weather forecast data by date to obtain a forecast data sequence; Extract some data with the latest collection date from the meteorological data, and sort the data in order of collection date to obtain the actual data sequence; The predicted data sequence is concatenated to the end of the actual data sequence to obtain the meteorological data sequence.

[0009] In an optional implementation, obtaining plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generating the irrigation demand of the branch canal based on the plot information includes: Determine the plots corresponding to the branch canals based on their geographical locations; Collect the crop types, crop planting area and plot humidity of the corresponding plots; Calculate the average humidity of the plot; Based on the crop type, the corresponding required humidity is retrieved from the crop information database; The humidity difference between the required humidity and the average humidity is calculated, and the irrigation water amount is calculated based on the humidity difference and the crop planting area.

[0010] In an optional embodiment, it also includes: If it is confirmed that there are multiple crop types on the plot, the irrigation water volume for each crop type is calculated separately, and the sum of the irrigation water volumes of multiple crop types is taken as the irrigation water volume for the plot; The sum of the irrigation water volumes of multiple plots corresponding to the branch canal is output as the irrigation demand of the branch canal.

[0011] In an optional embodiment, a water distribution model is constructed based on the predicted value of the main channel flow and the irrigation demand of each branch channel, including: Q represents the traffic forecast value, q j represents the water diversion flow of the jth branch canal, then the number of rotation irrigation groups is: M≤Q / q j ; Let the decision variable x ij ={0,1}, indicating the switch status of the outlet of the j-th branch canal of the i-th irrigation group, x ij =0 means the branch canal outlet is closed, x ij =1 means the branch canal outlet is open; t j The j-th outlet has a flow rate q j The time required to draw the required irrigation water, subscript i = 1, 2, ..., M; j = 1, 2, ..., N; The objective function for establishing the minimum water delivery time is: ; ; Among them, Q j is the irrigation water demand of the jth branch canal; Set constraints: Assuming the maximum allowable water delivery time of the water distribution channel is T, the sum of the water diversion time of each branch channel in each irrigation group shall not exceed the rotation period T; The outlet of any branch canal is opened only once during a rotation period.

[0012] In an optional implementation, solving the water distribution model to obtain an optimal water diversion plan includes: Based on the historical flow statistics of each branch canal, the water diversion flow value of each branch canal is set, and the water diversion flow value of each branch canal is substituted into the water distribution model; The water distribution model is solved by using a genetic algorithm to obtain the water distribution branch canals corresponding to each irrigation group.

[0013] In a second aspect, the present invention provides an irrigation channel water diversion optimization system, comprising: A flow prediction module, used for collecting meteorological data and predicting the main channel flow based on the meteorological data using a pre-trained prediction model; A demand assessment module is used to obtain the plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generate the irrigation demand of the branch canal based on the plot information; Model building module, used to build water distribution model based on the predicted value of main channel flow and irrigation demand of each branch channel; The model solving module is used to solve the water distribution model and obtain the optimal water diversion plan.

[0014] In a third aspect, a terminal is provided, including: A memory for storing an irrigation canal water diversion optimization program; A processor is used to implement the steps of the irrigation channel water diversion optimization method provided in the first aspect when executing the irrigation channel water diversion optimization program.

[0015] In a fourth aspect, a computer-readable storage medium is provided, on which an irrigation channel water diversion optimization program is stored. When the irrigation channel water diversion optimization program is executed by a processor, the steps of the irrigation channel water diversion optimization method provided in the first aspect are implemented.

[0016] The beneficial effect of the present invention lies in that the irrigation channel water diversion optimization method, system, terminal and storage medium provided by the present invention take into account the irrigation demand of each branch channel and the actual flow of the main channel, scientifically formulate the number of rotation irrigation groups and the water diversion branch channels included in each rotation irrigation group, rationally utilize water resources, and save irrigation time.

[0017] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0020] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0024] The irrigation channel water diversion optimization method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the irrigation channel water diversion optimization system runs in the computer device.

[0025] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be an irrigation canal water diversion optimization system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0026] like Figure 1 As shown, the method includes: S1, collecting meteorological data, and using a pre-trained prediction model to predict the main channel flow based on the meteorological data.

[0027] First, through professional meteorological monitoring equipment or data interfaces, we comprehensively collect key meteorological data including rainfall, temperature, humidity, wind speed, wind direction, etc. These data are crucial for the subsequent prediction of the flow of the main channel, because they can directly affect key parameters such as the water level, flow rate and evaporation of the river. Then, we use the prediction model based on machine learning or deep learning technology that has been trained in the early stage to conduct in-depth analysis of these meteorological data to predict the flow changes of the main channel in the future. This prediction process not only takes into account the current meteorological conditions, but also incorporates multiple factors such as historical flow data, topographic features, and possible seasonal changes, so as to ensure the accuracy and reliability of the prediction results.

[0028] S2, obtaining the plot information corresponding to the branch canal, wherein the plot information includes the crop type, area and plot humidity, and generating the irrigation demand of the branch canal based on the plot information.

[0029] Next, we turned to the detailed collection of information on the plots corresponding to the branch canals. This information covers key indicators such as crop types, planting areas, and the current humidity conditions of the plots. The type of crop determines its demand for water and the period of demand, the planting area is directly related to the amount of irrigation, and the humidity of the plot reflects the current soil moisture conditions and is an important basis for formulating irrigation plans. Based on this plot information, we use a professional agricultural irrigation demand calculation model, taking into account factors such as the crop growth cycle, transpiration, and soil water retention capacity, to accurately calculate the irrigation needs of each branch canal. This step ensures the pertinence and effectiveness of the irrigation plan and avoids the waste of water resources.

[0030] S3, construct a water distribution model based on the predicted value of the main canal flow and the irrigation demand of each branch canal.

[0031] After obtaining the predicted value of the main canal flow and the irrigation demand of each branch canal, we entered the stage of constructing the water distribution model. This model aims to achieve the reasonable allocation of irrigation water resources to meet the irrigation needs of each branch canal, while ensuring the stability and sustainable use of the main canal flow. During the construction process, we fully considered factors such as the dynamic changes of the main canal flow, the priority of the branch canal irrigation demand, and possible irrigation conflicts, and solved the optimal water distribution plan through mathematical optimization methods (such as linear programming, nonlinear programming, etc.).

[0032] S4, solve the water distribution model to obtain the optimal water diversion plan.

[0033] The last step is to solve the water distribution model to obtain the optimal water diversion plan. We use advanced computing technology and optimization algorithms to iteratively solve the model until we find a solution that satisfies all constraints and achieves the optimal objective function. This solution is the optimal water diversion plan, which specifies in detail the irrigation water volume and irrigation time of each branch canal in different time periods, as well as the control strategy of the main canal flow. By implementing this plan, we can achieve accurate allocation and efficient use of irrigation water resources, providing strong support for agricultural production. At the same time, this plan also has a certain degree of flexibility and adaptability, and can be dynamically adjusted and optimized according to changes in actual conditions.

[0034] Based on step S1, a specific example is given, including: S101, collecting meteorological data, wherein the meteorological data includes temperature, humidity, and precipitation.

[0035] Collect real-time weather data including temperature, humidity, and precipitation from weather monitoring stations or data providers.

[0036] Specific acquisition methods include: using API interfaces or data crawling tools to obtain data from online meteorological databases. The data format should be unified to facilitate subsequent processing and analysis. Data should be updated in real time to ensure the timeliness of information.

[0037] That is, the weather data is actually the weather data for the current time and a certain period of time in the past.

[0038] S102, obtaining weather forecast data, wherein the weather forecast data includes predicted temperature, predicted humidity and predicted precipitation.

[0039] Use professional weather forecast services or models, such as numerical weather prediction (NWP) models. The time range of forecast data should cover the period required for main channel flow forecast. The data precision and accuracy must meet the requirements of the forecast model. Obtain weather forecast data for a period of time in the future, including predicted temperature, predicted humidity, and predicted precipitation.

[0040] S103, integrating meteorological data and meteorological forecast data into a meteorological data sequence.

[0041] Sort the meteorological forecast data by date to obtain a forecast data sequence; extract some data whose collection date is within the latest period from the meteorological data, and sort the partial data in chronological order of collection date to obtain an actual data sequence; concatenate the forecast data sequence to the end of the actual data sequence to obtain a meteorological data sequence.

[0042] Sort the forecast data by date to ensure data continuity. Extract some data within the latest period from the actual data and sort them by collection date. Splice the forecast data sequence to the end of the actual data sequence to form a complete meteorological data sequence. During the data splicing process, ensure the consistency of data type and format.

[0043] S104, inputting the meteorological data sequence into a pre-trained long short-term memory neural network model to obtain the flow forecast value of the main channel in the future period.

[0044] The LSTM model should be trained with similar historical data in advance and its prediction performance should be verified. The integrated meteorological data sequence is input into the model to predict the flow. The prediction results are output, including the flow values ​​for each future period.

[0045] In a specific example, the implementation code is as follows: # Assume that model is a trained LSTM model # weather_data_array is the prepared input data # Preprocess the input data to meet the model input requirements (such as standardization, normalization, etc.) # Specific preprocessing steps are omitted here # Use the model to make predictions predicted_flow = model.predict(weather_data_array[:, 1:])# Assume that the date column is not involved in the prediction, only temperature, humidity and precipitation are used # Output prediction results for i, flow in enumerate(predicted_flow): print(f"The predicted flow rate for the future {i+1} period is: {flow[0]} cubic meters / second") Based on step S2, a specific example is given, including: S201, determine the plot corresponding to the branch canal based on the geographical location of the branch canal.

[0046] Using geographic information system (GIS) technology, the geographical location information of the branch canal is spatially matched with the plots in the plot information database.

[0047] The plot information database should contain information such as the plot's geographical location (such as polygon coordinates) and plot number.

[0048] Through spatial query or spatial join operation, find out the plots that intersect or are adjacent to the branch canal geographical location.

[0049] S202, collecting the crop types, crop planting areas and plot humidity of the corresponding plots.

[0050] The plot information database should include information such as crop types and planting areas on the plots.

[0051] The plot moisture data can be collected through soil moisture sensors or obtained from other data sources.

[0052] The collected data should be stored in a structured data structure to facilitate subsequent processing.

[0053] S203, calculating the average humidity of the plot.

[0054] If there are multiple humidity sensors in a plot, the average humidity collected by these sensors should be calculated.

[0055] If there is only one humidity sensor in the plot, the humidity value of the sensor is directly used as the humidity of the plot.

[0056] S204, retrieving the corresponding required humidity from the crop information database based on the crop type.

[0057] The crop information database should contain the correspondence between crop types and required humidity. Assume that there is a crop information database crop_info_db, which contains the correspondence between crop types and required humidity: the required humidity of crop A is 0.6 (relative humidity), the required humidity of crop B is 0.7, and other crops and their required humidity.

[0058] Use the crop type as the key to retrieve the corresponding required humidity from the crop information database.

[0059] S205, calculating the humidity difference between the required humidity and the average humidity, and calculating the irrigation water amount based on the humidity difference and the crop planting area.

[0060] Humidity difference = required humidity - average humidity.

[0061] The amount of irrigation water can be calculated using certain conversion formulas, such as based on soil bulk density, soil depth, moisture difference and other factors.

[0062] The amount of irrigation water should be taken into account the area under which the crop is grown to calculate the total amount of irrigation water.

[0063] If there are multiple crop types on a plot, the irrigation water volume for each crop type is calculated separately, and the sum of the irrigation water volumes of the multiple crop types is used as the irrigation water volume for the plot; the sum of the irrigation water volumes of the multiple plots corresponding to the branch canal is output as the irrigation demand of the branch canal.

[0064] Specifically, the processing methods for multiple crop types include: For each plot, if it contains multiple crop types, we need to calculate the irrigation water volume for each crop type separately. This means that the plot information needs to include the planting area of ​​each crop type. Use the irrigation water volume calculation formula mentioned earlier, but this time calculate it separately for each crop type. Add up the irrigation water volumes of all crop types in the plot to get the irrigation water volume for the plot. For each plot corresponding to the branch canal, add up its irrigation water volume to get the total irrigation demand of the branch canal.

[0065] Based on step S3, in a specific example, the following contents are included: Q represents the traffic forecast value, q j represents the water diversion flow of the jth branch canal, then the number of rotation irrigation groups is: M≤Q / q j ; Let the decision variable x ij ={0,1}, indicating the switch status of the outlet of the j-th branch canal of the i-th irrigation group, x ij =0 means the branch canal outlet is closed, x ij =1 means the branch canal outlet is open; t j The j-th outlet has a flow rate q j The time required to draw the required irrigation water, subscript i = 1, 2, ..., M; j = 1, 2, ..., N; The objective function for establishing the minimum water delivery time is: ; ; Among them, Q j is the irrigation water demand of the jth branch canal; Set constraints: Assuming the maximum allowable water delivery time of the water distribution channel is T, the sum of the water diversion time of each branch channel in each irrigation group shall not exceed the rotation period T; The outlet of any branch canal is opened only once during a rotation period.

[0066] Step S4 is to solve the water distribution model established in S3. In a specific example, the solution method includes: S401, based on the historical flow statistics of each branch canal, set the water diversion flow value of each branch canal, and substitute the water diversion flow value of each branch canal into the water distribution model.

[0067] Historical flow statistics: Collect flow data of each branch canal in the past year, including daily, weekly, monthly or annual average flow, maximum flow, minimum flow, etc.

[0068] According to historical flow statistics, a reasonable water diversion flow value (q j ). This value does not exceed the carrying capacity of the branch canal.

[0069] Taking into account that the flow rate may vary over time, you can set water diversion flow values ​​for multiple time periods (such as day, night, peak irrigation period, etc.).

[0070] In some embodiments of the present application, since different branch canals are located in different terrain conditions, for example, the branch canals are located in a flat area, the branch canals are located downhill, and the branch canals have different degrees of curvature, the amount of water lost is also different. Therefore, the hydrodynamic physical model can be used to pre-consider the simulated water diversion volume required for different branch canals to ensure the irrigation water demand.

[0071] Based on this, the irrigation water demand of each branch canal can be input into the corresponding hydrodynamic physical model to obtain the simulated water diversion flow of each branch canal, and the simulated water diversion flow can be determined as the water diversion flow value.

[0072] It should be noted that the hydrodynamics software is used to construct the hydrodynamics physical model. The topographic data and the geometric parameters of the branch canal (such as width, depth, roughness, etc.) are input into the hydrodynamics physical model to obtain the hydrodynamics physical model of each branch canal.

[0073] Furthermore, since there is no way to accurately collect the actual amount of water flowing into the fields, there is no way to compare the actual difference between the actual inflow and the irrigation demand. Under this premise, as the branch canal is used for a longer time, the actual physical structure of the branch canal will change slightly, and this slight change cannot be discovered by the management personnel in time, so there is no way to modify the parameters of the hydrodynamic physical model in time.

[0074] Therefore, at this time, the hydrodynamic model is different from the actual physical conditions of the branch canal. Therefore, it is necessary to verify the accuracy of the hydrodynamic physical model.

[0075] Specifically, the difference between the accuracy verification time of the hydrodynamic physical model and the current time is determined.

[0076] If the difference is greater than the preset duration, the actual water flow parameters collected for each branch canal during multiple irrigation processes and the simulated water flow parameters of the hydrodynamic physical model for each irrigation operation are extracted from the historical flow statistics of each branch canal. Among them, the simulated water flow parameters include simulated water diversion flow, simulation duration, simulated flow rate, and simulated irrigation water demand. The actual water flow parameters include actual water diversion flow, actual duration, and actual flow rate. It can be understood that the actual water diversion flow is greater than or equal to the simulated water diversion flow. When the hydrodynamic physical model is not much different from the actual conditions of the branch canal, the simulated water diversion flow does not need to be corrected, and the simulated water diversion flow is equal to the actual water diversion flow.

[0077] The characteristic relationship between the simulated water flow parameters and the actual water flow parameters is extracted to obtain the difference coefficient between the simulated water flow parameters and the actual water flow parameters, and the difference coefficient is used as the correction compensation coefficient. For example, the simulated water flow parameters and the actual water flow parameters of multiple irrigations are input into the corrected flow prediction neural network model to obtain the correction compensation coefficient. The correction compensation coefficient is multiplied by the simulated water diversion flow to obtain the water diversion flow value of each branch canal. It should be noted that in actual scenarios, due to the loss of use of branch canals, the water loss is usually increasing, resulting in less and less actual water flowing into the fields. Therefore, the compensation coefficient is greater than 1, so that the actual water diversion flow can be higher.

[0078] It should be noted that the sample simulated flow parameters and sample actual flow parameters of each branch canal under multiple irrigation in the hydrodynamic physical model, as well as the sample correction coefficient of each branch canal are extracted. The sample simulated flow parameters and sample actual flow parameters of multiple irrigations are used as sample inputs, and the sample correction coefficient of each branch canal is used as a sample label to perform supervised training on the initial corrected flow prediction neural network model to obtain a corrected flow prediction neural network model.

[0079] S402, solving the water distribution model using a genetic algorithm to obtain the water distribution branch canals corresponding to each irrigation group.

[0080] Encoding: Transform the decision variable x ij The code is a chromosome in the genetic algorithm, and each chromosome represents a possible combination of rotation irrigation grouping and branch canal outlet switch status.

[0081] Initial population: A set of chromosomes is randomly generated as the initial population.

[0082] Fitness function: The fitness value of each chromosome is calculated according to the objective function, that is, minimizing the weighted sum of the water diversion time of all branch canals.

[0083] Selection: Select a part of chromosomes as parents according to the fitness value to produce the next generation.

[0084] Crossover: Perform a crossover operation on the selected parent chromosome to generate new daughter chromosomes.

[0085] Mutation: Randomly mutate the chromosomes of offspring to increase the diversity of the population.

[0086] Iteration: Repeat the selection, crossover, and mutation operations until the preset number of iterations is reached or the termination condition is met.

[0087] Decoding: The final chromosome is decoded into the optimal solution for irrigation grouping and branch canal outlet switch status.

[0088] Assume there are 4 branch canals (N=4), and the historical flow statistics and irrigation water demand of each branch canal are known. A water distribution model can be constructed according to the above steps and solved using a genetic algorithm.

[0089] Set the diversion flow value: According to historical data and irrigation needs, set a diversion flow value q for each branch canal. j .

[0090] Building the model: Using decision variables x ij , objective function and constraints to build an optimization model.

[0091] Genetic algorithm solution: Set parameters such as initial population size, crossover probability, mutation probability, and run the genetic algorithm to solve.

[0092] Result output: Assume that the final solution is: the first round of irrigation includes the opening of branch canals 1 and 3, and the second round of irrigation includes the opening of branch canals 2 and 4. The water diversion flow value of each branch canal is also determined accordingly.

[0093] In some embodiments, the irrigation channel water diversion optimization system may include multiple functional modules composed of computer program segments. The computer program of each program segment in the irrigation channel water diversion optimization system may be stored in the memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) The function of optimizing water diversion in irrigation canals.

[0094] In this embodiment, the irrigation channel water diversion optimization system can be divided into multiple functional modules according to the functions it performs, such as Figure 2As shown. The functional modules of the system 200 may include: a traffic prediction module 210, a demand assessment module 220, a model building module 230, and a model solving module 240. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0095] A flow prediction module, used for collecting meteorological data and predicting the main channel flow based on the meteorological data using a pre-trained prediction model; A demand assessment module is used to obtain the plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generate the irrigation demand of the branch canal based on the plot information; Model building module, used to build water distribution model based on the predicted value of main channel flow and irrigation demand of each branch channel; The model solving module is used to solve the water distribution model and obtain the optimal water diversion plan.

[0096] Optionally, as an embodiment of the present invention, collecting meteorological data, and using a pre-trained prediction model to predict the main channel flow based on the meteorological data, includes: Collecting meteorological data, including temperature, humidity, and precipitation; Acquiring weather forecast data, wherein the weather forecast data includes predicted temperature, predicted humidity and predicted precipitation; Integrate meteorological data and meteorological forecast data into meteorological data series; The meteorological data sequence is input into a pre-trained long short-term memory neural network model to obtain the flow prediction value of the main channel in the future period.

[0097] Optionally, as an embodiment of the present invention, the meteorological data and the meteorological forecast data are integrated into a meteorological data sequence, including: Sort the weather forecast data by date to obtain a forecast data sequence; Extract some data with the latest collection date from the meteorological data, and sort the data in order of collection date to obtain the actual data sequence; The predicted data sequence is concatenated to the end of the actual data sequence to obtain the meteorological data sequence.

[0098] Optionally, as an embodiment of the present invention, obtaining plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generating the irrigation demand of the branch canal based on the plot information includes: Determine the plots corresponding to the branch canals based on their geographical locations; Collect the crop types, crop planting area and plot humidity of the corresponding plots; Calculate the average humidity of the plot; Based on the crop type, the corresponding required humidity is retrieved from the crop information database; The humidity difference between the required humidity and the average humidity is calculated, and the irrigation water amount is calculated based on the humidity difference and the crop planting area.

[0099] Optionally, as an embodiment of the present invention, it further includes: If it is confirmed that there are multiple crop types on the plot, the irrigation water volume for each crop type is calculated separately, and the sum of the irrigation water volumes of multiple crop types is taken as the irrigation water volume for the plot; The sum of the irrigation water volumes of multiple plots corresponding to the branch canal is output as the irrigation demand of the branch canal.

[0100] Optionally, as an embodiment of the present invention, a water distribution model is constructed based on the predicted value of the main channel flow and the irrigation demand of each branch channel, including: Q represents the traffic forecast value, q j represents the water diversion flow of the jth branch canal, then the number of rotation irrigation groups is: M≤Q / q j ; Let the decision variable x ij ={0,1}, indicating the switch status of the outlet of the j-th branch canal of the i-th irrigation group, x ij =0 means the branch canal outlet is closed, x ij =1 means the branch canal outlet is open; t j The j-th outlet has a flow rate q j The time required to draw the required irrigation water, subscript i = 1, 2, ..., M; j = 1, 2, ..., N; The objective function for establishing the minimum water delivery time is: ; ; Among them, Q j is the irrigation water demand of the jth branch canal; Set constraints: Assuming the maximum allowable water delivery time of the water distribution channel is T, the sum of the water diversion time of each branch channel in each irrigation group shall not exceed the rotation period T; The outlet of any branch canal is opened only once during a rotation period.

[0101] Optionally, as an embodiment of the present invention, solving the water distribution model to obtain the optimal water diversion plan includes: Based on the historical flow statistics of each branch canal, the water diversion flow value of each branch canal is set, and the water diversion flow value of each branch canal is substituted into the water distribution model; The water distribution model is solved by using a genetic algorithm to obtain the water distribution branch canals corresponding to each irrigation group.

[0102] Figure 3 The present invention is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the irrigation channel water diversion optimization method provided in an embodiment of the present invention.

[0103] The terminal 300 may include: a processor 310, a memory 320 and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0104] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can perform some or all of the steps in the following method embodiments.

[0105] The processor 310 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0106] The communication unit 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0107] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0108] Therefore, the present invention takes into account the irrigation needs of each branch canal and the actual flow rate of the main canal, scientifically formulates the number of rotation irrigation groups and the water diversion branch canals included in each rotation irrigation group, rationally utilizes water resources, and saves irrigation time. The technical effects that can be achieved by this embodiment can be found in the description above and will not be repeated here.

[0109] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0110] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0111] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0112] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0114] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A method for optimizing irrigation canal water diversion, characterized in that: include: Collect meteorological data and use a pre-trained prediction model to predict the flow of the main channel based on the meteorological data; Acquire the plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generate the irrigation demand of the branch canal based on the plot information; Construct a water distribution model based on the predicted value of the main canal flow and the irrigation demand of each branch canal; The water distribution model is solved to obtain the optimal water diversion plan.

2. The method according to claim 1, characterized in that Collect meteorological data and use a pre-trained prediction model to predict the main channel flow based on the meteorological data, including: Collecting meteorological data, including temperature, humidity, and precipitation; Acquiring weather forecast data, wherein the weather forecast data includes predicted temperature, predicted humidity and predicted precipitation; Integrate meteorological data and meteorological forecast data into meteorological data series; The meteorological data sequence is input into a pre-trained long short-term memory neural network model to obtain the flow prediction value of the main channel in the future period.

3. The method according to claim 2, characterized in that Integrate meteorological data and meteorological forecast data into meteorological data series, including: Sort the weather forecast data by date to obtain a forecast data sequence; Extract some data with the latest collection date from the meteorological data, and sort the data in order of collection date to obtain the actual data sequence; The predicted data sequence is concatenated to the end of the actual data sequence to obtain the meteorological data sequence.

4. The method according to claim 1, characterized in that: Obtaining the plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generating the irrigation demand of the branch canal based on the plot information, including: Determine the plots corresponding to the branch canals based on their geographical locations; Collect the crop types, crop planting area and plot humidity of the corresponding plots; Calculate the average humidity of the plot; Based on the crop type, the corresponding required humidity is retrieved from the crop information database; The humidity difference between the required humidity and the average humidity is calculated, and the irrigation water amount is calculated based on the humidity difference and the crop planting area.

5. The method according to claim 4, characterized in that Also includes: If it is confirmed that there are multiple crop types on the plot, the irrigation water volume for each crop type is calculated separately, and the sum of the irrigation water volumes of multiple crop types is taken as the irrigation water volume for the plot; The sum of the irrigation water volumes of multiple plots corresponding to the branch canal is output as the irrigation demand of the branch canal.

6. The method according to claim 2, characterized in that The water distribution model is constructed based on the predicted value of the main canal flow and the irrigation demand of each branch canal, including: Q represents the traffic forecast value, q j represents the water diversion flow of the jth branch canal, then the number of rotation irrigation groups is: M≤Q / q j ; Let the decision variable x ij ={0,1}, indicating the switch status of the outlet of the j-th branch canal of the i-th irrigation group, x ij =0 means the branch canal outlet is closed, x ij =1 means the branch canal outlet is open; t j The j-th outlet has a flow rate q j The time required to draw the required irrigation water, subscript i=1, 2, ..., M; j=1, 2, ..., N; The objective function for establishing the minimum water delivery time is: ； ； Among them, Q j is the irrigation water demand of the jth branch canal; Set constraints: Assuming the maximum allowable water delivery time of the water distribution channel is T, the sum of the water diversion time of each branch channel in each irrigation group shall not exceed the rotation period T; The outlet of any branch canal is opened only once during a rotation period.

7. The method according to claim 6, characterized in that Solve the water distribution model to obtain the optimal water diversion plan, including: Based on the historical flow statistics of each branch canal, the water diversion flow value of each branch canal is set, and the water diversion flow value of each branch canal is substituted into the water distribution model; The water distribution model is solved by using a genetic algorithm to obtain the water distribution branch canals corresponding to each irrigation group.

8. An irrigation canal water diversion optimization system, characterized in that: include: A flow prediction module, used for collecting meteorological data and predicting the main channel flow based on the meteorological data using a pre-trained prediction model; A demand assessment module is used to obtain the plot information corresponding to the branch canal, the plot information including crop type, area and plot humidity, and generate the irrigation demand of the branch canal based on the plot information; Model building module, used to build water distribution model based on the predicted value of main channel flow and irrigation demand of each branch channel; The model solving module is used to solve the water distribution model and obtain the optimal water diversion plan.

9. A terminal, characterized in that: include: A memory for storing an irrigation canal water diversion optimization program; A processor is used to implement the steps of the irrigation channel water diversion optimization method as described in any one of claims 1 to 7 when executing the irrigation channel water diversion optimization program.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores an irrigation channel water diversion optimization program, and when the irrigation channel water diversion optimization program is executed by the processor, the steps of the irrigation channel water diversion optimization method according to any one of claims 1 to 7 are implemented.

Images