A method and system for inverting water supply from water source in irrigation area during drought period

Abstract

The present invention relates to the technical field of irrigation area water resource data processing, and provides a method and system for inverting water supply from a water source in an irrigation area during a drought. The method for inverting water supply from a water source in an irrigation area during a drought includes: calculating agricultural predicted water demand; extracting a number of periodic characteristic parameters from a number of historical non-agricultural water use data; training a number of prediction models to obtain non-agricultural predicted water demand; obtaining water and soil data between a reservoir group and an irrigation area, and constructing an evolution model; obtaining rainfall and the discharge flow process of a reservoir group to calculate the incoming water flow process at the head of the irrigation area; calculating the water resource surplus of the irrigation area; and establishing a scheme optimization model based on an evolution model and a genetic algorithm to obtain the final reservoir group discharge plan, and supplying water to the irrigation area based on the final reservoir group discharge plan. Through data and model calculation, the final reservoir group discharge plan is obtained, providing data and scheme support for irrigation area water replenishment during the drought period.

Description

Technical Field

[0001] The present invention relates to the technical field of irrigation area water resource data processing, and in particular to a method and system for inverting water supply from a water source in an irrigation area during a drought period. Background Art

[0002] At present, most large and medium-sized irrigation areas use reservoirs and other water storage projects as water sources for water diversion and irrigation. After decades of water conservancy construction, an irrigation model has been formed with water storage projects as the leader and canals, pipelines and other water transfer projects as the backbone.

[0003] In the process of developing smart irrigation districts, people focus on the water resource allocation and gate group scheduling within the irrigation district, and build a joint water transmission and distribution scheduling system within the irrigation district. However, in the dry season and at the peak of irrigation, the water demand for agriculture, industry, life, and ecology in the irrigation district may be far greater than the water supply at the head of the irrigation district, and it is necessary to coordinate one or more water sources upstream to replenish water, that is, it is necessary to coordinate the upstream reservoir or reservoir group to discharge water to ensure the irrigation, life, and production needs in the irrigation district during the drought period.

[0004] Determining the water replenishment plan for the upstream water source requires the irrigation district to make accurate water supply demands to the water source. However, determining the water supply of the irrigation district water source is a complex process involving many factors, such as the type of water demand within the irrigation district, the land topography of the discharge path, the capacity of the reservoir itself, etc. The existing method for determining the water supply of the irrigation district water source does not take factors into consideration comprehensively and lacks specific inversion methods, which makes it difficult to provide accurate data and program support when the upstream water source is needed to replenish water during the drought period of the irrigation district. Summary of the invention

[0005] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method and system for inverting the water supply of water sources in irrigation areas during drought periods. The present invention analyzes multiple influencing factors, constructs an evolution model of water and soil characteristics of the route from the upstream reservoir group to the irrigation area, and establishes a quantifiable inversion process for the water supply of water sources in the irrigation area, thereby solving the technical problem of lack of accurate data and solution support when irrigation areas demand water supply from water sources during drought periods.

[0006] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0007] A method for inverting water supply from a water source in an irrigation area during a drought period comprises the following steps:

[0008] Acquire soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, acquire weather forecast data, and calculate agricultural predicted water demand based on the soil moisture data, crop characteristic data, soil bulk density data and weather forecast data;

[0009] Obtaining the total number of non-agricultural water users in the irrigation area and a number of historical non-agricultural water use data, and extracting a number of periodic characteristic parameters from the historical non-agricultural water use data;

[0010] Based on the total quantity, a plurality of prediction modules and a plurality of discarding layers are constructed, and a plurality of the prediction modules are associated with a plurality of the discarding layers to form a plurality of prediction models, and a plurality of the prediction models are trained based on a plurality of the periodic characteristic parameters to obtain non-agricultural predicted water demand;

[0011] Acquire water and soil data between the reservoir group and the irrigation area, and construct an evolution model;

[0012] Obtaining rainfall and the discharge flow process of the reservoir group, and inputting them into the evolution model to calculate the water flow process at the head of the irrigation area;

[0013] Based on the water flow process at the canal head of the irrigation area, the total water flow at the canal head of the irrigation area is calculated, and based on the agricultural predicted water demand, the non-agricultural predicted water demand and the total water flow, the water resource surplus of the irrigation area is calculated;

[0014] Based on the evolutionary model and the genetic algorithm, a scheme optimization model is established, and based on the discharge flow process of the reservoir group and the water resource surplus, the objective function in the scheme optimization model is calculated to screen several reservoir group discharge scheme samples to obtain the final reservoir group discharge scheme, and water is supplied to the irrigation area based on the final reservoir group discharge scheme.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: by acquiring a variety of data in the irrigation area, agricultural and non-agricultural water demands are taken into consideration; for agricultural water use, in addition to acquiring the soil moisture data, crop characteristics and soil-related properties are also analyzed, which is beneficial to obtaining accurate water demand data; and combined with weather forecasts, water demand data are predicted and optimized, and accurate predictions are made for farmland water use during droughts to obtain the agricultural predicted water demand; for non-agricultural water use, a mathematical model is used to analyze the periodic characteristics of several non-agricultural water users, and the periodic characteristic parameters that can be used to train the model are extracted, and the water demand is obtained by mathematical methods. The non-agricultural predicted water demand; the land morphology, land use, vegetation coverage and other factors of the route from the upstream reservoir group to the irrigation area are reflected through the water and soil data, and the evolution model is constructed, the inflow flow process at the head of the irrigation area is calculated through the evolution model, the inflow flow process that continuously changes with time is reflected by data, and the total inflow is further calculated and extracted to obtain the data of the water resource surplus of the irrigation area; by establishing the scheme optimization model and adopting multiple iterations of the genetic algorithm, the final reservoir group discharge scheme is accurately obtained to provide data and scheme support for water replenishment in the irrigation area during drought periods.

[0016] Furthermore, the step of obtaining soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, obtaining weather forecast data, and calculating the predicted agricultural water demand based on the soil moisture data, the crop characteristic data, the soil bulk density data and the weather forecast data includes:

[0017] Calculating the amount of water shortage for crop irrigation based on the soil moisture data, the crop characteristic data and the soil bulk density data;

[0018] Based on the weather forecast data, the Thornthwaite model is used to predict the potential evapotranspiration of crops;

[0019] The predicted agricultural water demand is calculated based on the crop irrigation water shortage, the crop potential evapotranspiration and the weather forecast data.

[0020] Furthermore, the step of calculating the crop irrigation water shortage based on the soil moisture data, the crop characteristic data and the soil bulk density data includes:

[0021] Extracting the crop root activity layer depth from the crop characteristic data, and determining the planned soil moist layer depth based on the crop root activity layer depth;

[0022] Extracting soil water holding capacity and current soil water content from the soil moisture data;

[0023] Based on the soil bulk density data, calculating the average soil bulk density;

[0024] The water shortage for crop irrigation is calculated based on the planned soil moistening layer depth, the soil water holding capacity, the current soil moisture content and the average soil bulk density.

[0025] Furthermore, the step of calculating the predicted agricultural water demand based on the crop irrigation water shortage, the crop potential evapotranspiration and the weather forecast data includes:

[0026] Calculating the future soil moisture content based on the crop potential evapotranspiration and the current soil moisture content, and updating the crop irrigation water shortage to the crop irrigation predicted water shortage according to the crop irrigation water shortage and the future soil moisture content;

[0027] The future rainfall data of the irrigation area is extracted from the weather forecast data, and the predicted agricultural water demand is calculated based on the predicted water shortage of crop irrigation and the future rainfall data of the irrigation area.

[0028] Furthermore, the step of extracting a plurality of periodic characteristic parameters from a plurality of historical non-agricultural water use data comprises:

[0029] Standardizing a plurality of the historical non-agricultural water use data into a plurality of water use data to be extracted;

[0030] Based on the characteristics of the plurality of non-agricultural water users, an extraction module is constructed, and the plurality of water use data to be extracted are input into the extraction module to obtain a plurality of periodic characteristic parameters.

[0031] Furthermore, the number of the prediction modules and the number of the discarded layers are three times the total number, the discard rate of the discarded layer is 0.3, and the number of the prediction models is equal to the total number.

[0032] Furthermore, the evolution model includes a hydrological sub-model and a river flow evolution sub-model, and the step of inputting the evolution model to calculate the water flow process at the head of the irrigation area includes:

[0033] Inputting the rainfall into the hydrological sub-model to obtain the flow generation and convergence between the reservoir group and the head of the irrigation area;

[0034] The discharge scheme of the reservoir group is extracted from the discharge process of the reservoir group, and the discharge scheme of the reservoir group and the flow generation and confluence of the interval are used as boundary conditions of the river flow evolution sub-model to calculate the inflow flow process at the head of the irrigation area.

[0035] Furthermore, the reservoir group includes several reservoirs, and the formula of the objective function is:

[0036]

[0037] in, is the objective function, is the weight function of water resource surplus and reservoir group dispatching operation cost, is the first Reservoir Hourly discharge flow, , is the length of the forecast period in days, is the first weight factor, For the future The water resource surplus of the irrigation area per day, is the second weight factor, For the future The operation cost of the reservoir group dispatching per day, The formula is:

[0038]

[0039] in, , is the total number of reservoirs, , For the future Day's The operation cost of a reservoir is The formula is:

[0040]

[0041] in, is the first Reservoir Hourly discharge flow.

[0042] Furthermore, after the step of calculating the objective function in the solution optimization model, the method further includes:

[0043] Obtaining the water storage capacity and inflow of the reservoir, and extracting the reservoir discharge from the discharge process of the reservoir group to form a water balance constraint;

[0044] Obtain the minimum water level and the maximum water level of the reservoir to form the reservoir water level constraint;

[0045] Obtain the maximum discharge capacity of the reservoir to form the reservoir discharge capacity constraint;

[0046] The water balance constraint, the reservoir water level constraint and the reservoir discharge capacity constraint constitute constraint conditions, and the constraint conditions are added to the solution optimization model.

[0047] The present invention also provides a drought-period irrigation area water source land water supply inversion system, which is applied to the drought-period irrigation area water source land water supply inversion method as described in the above technical solution, and the system comprises:

[0048] The first prediction module is used to obtain soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, obtain weather forecast data, and calculate the agricultural predicted water demand based on the soil moisture data, the crop characteristic data, the soil bulk density data and the weather forecast data;

[0049] An extraction module, used to obtain the total number of non-agricultural water users in the irrigation area and a plurality of historical non-agricultural water use data, and extract a plurality of periodic characteristic parameters from the plurality of historical non-agricultural water use data;

[0050] A second prediction module is used to construct a plurality of prediction modules and a plurality of discarding layers based on the total quantity, and associate the plurality of prediction modules with the plurality of discarding layers to form a plurality of prediction models, and train the plurality of prediction models based on the plurality of periodic characteristic parameters to obtain non-agricultural predicted water demand;

[0051] A construction module is used to obtain water and soil data between the reservoir group and the irrigation area and construct an evolution model;

[0052] A flow module, used for obtaining rainfall and the discharge flow process of the reservoir group, and inputting the flow into the evolution model to calculate the flow process of the water flow at the head of the irrigation area;

[0053] A surplus module, used to calculate the total amount of water inflow at the head of the irrigation area based on the water inflow flow process at the head of the irrigation area, and calculate the water resource surplus of the irrigation area based on the agricultural predicted water demand, the non-agricultural predicted water demand and the total amount of water inflow;

[0054] An optimization module is used to establish a scheme optimization model based on the evolution model and the genetic algorithm, and calculate the objective function in the scheme optimization model based on the discharge flow process of the reservoir group and the water resource surplus, so as to screen several reservoir group discharge plan samples to obtain the final reservoir group discharge plan, and supply water to the irrigation area based on the final reservoir group discharge plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flowchart of a method for inverting water supply from a water source in an irrigation area during a drought period in an embodiment of the present invention;

[0056] Figure 2 It is a structural schematic diagram of a water supply inversion system for a water source area in an irrigation area during a drought period in another embodiment of the present invention;

[0057] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0058] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0059] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0061] See also Figure 1 The method for inverting water supply from a water source area in a drought period in an embodiment of the present invention comprises the following steps:

[0062] Step S10: obtaining soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, obtaining weather forecast data, and calculating agricultural predicted water demand based on the soil moisture data, the crop characteristic data, the soil bulk density data and the weather forecast data;

[0063] The specific water demand in the irrigation area is diverse, including agricultural irrigation water, domestic water, industrial water and ecological water, etc. Preferably, it is divided into two major categories: agricultural water and non-agricultural water. It can be understood that the water supply inversion method of the irrigation area water source during the drought period includes different types of water demand into the analysis, which is beneficial to increase the comprehensiveness of the inversion method. Among them, the analysis and calculation of agricultural water use specific to crop characteristics and soil characteristics is beneficial to provide data support.

[0064] Specifically, the step S10 includes:

[0065] S110: Calculating the amount of water shortage for crop irrigation based on the soil moisture data, the crop characteristic data and the soil bulk density data;

[0066] Preferably, the soil moisture data is obtained through field soil moisture detection, the crop characteristic data includes the root activity layer and suitable moisture content corresponding to different types of crops at different growth stages, and the soil bulk density data depends on the soil texture, structure, organic content and various natural factors and artificial management factors. The soil bulk density value of loose porous structure or artificial cultivation with a large number of large pores is small, and vice versa. The reference value of soil bulk density is different for different types of soil. For example, the reference value of bulk density of grass ash soil is 1.33 tons per cubic meter, the reference value of bulk density of gray forest soil is 1.29 tons per cubic meter, and the reference value of black calcium soil is 1.03 tons per cubic meter. When the soil bulk density data is actually obtained, the bulk density parameters are determined by sampling and weighing. It can be understood that the detailed data is conducive to more accurate data analysis and more reliable prediction of water demand.

[0067] Furthermore, the S110 specifically includes:

[0068] Extracting the crop root activity layer depth from the crop characteristic data, and determining the planned soil moist layer depth based on the crop root activity layer depth;

[0069] Extracting soil water holding capacity and current soil water content from the soil moisture data;

[0070] Based on the soil bulk density data, calculating the average soil bulk density;

[0071] The water shortage for crop irrigation is calculated based on the planned soil moistening layer depth, the soil water holding capacity, the current soil moisture content and the average soil bulk density.

[0072] Preferably, the water demand of dryland crops in farmland is established by the depth of the planned soil moistening layer, the average soil bulk density at the depth corresponding to the planned soil moistening layer depth, the soil water holding capacity at the depth and the soil moisture content at the depth. The irrigation water deficit of the dryland crops can be obtained by multiplying the difference between the soil water holding capacity at the depth and the soil moisture content at the depth by the average soil bulk density at the depth. In addition to the irrigation water deficit of the dryland crops, if the irrigation area includes paddy crops, the water consumption required for the paddy crops can be obtained through soil moisture detection. It can be understood that the irrigation water deficit of the crops can be calculated in detail according to the types and distribution of crops in the farmland in the irrigation area.

[0073] S120: Based on the weather forecast data, predicting the potential evapotranspiration of crops using the Thornthwaite model;

[0074] Preferably, the monthly average temperature and the annual heat index are obtained to calculate the potential evapotranspiration of the crops.

[0075] S130: Calculate the predicted agricultural water demand based on the crop irrigation water shortage, the crop potential evapotranspiration and the meteorological forecast data.

[0076] It is understandable that accurate prediction of agricultural water demand requires consideration of water replenishment to the irrigation area by future rainfall, as well as the impact of future crop evapotranspiration on current soil moisture content.

[0077] Furthermore, the S130 specifically includes:

[0078] Calculating the future soil moisture content based on the crop potential evapotranspiration and the current soil moisture content, and updating the crop irrigation water shortage to the crop irrigation predicted water shortage according to the crop irrigation water shortage and the future soil moisture content;

[0079] The future rainfall data of the irrigation area is extracted from the weather forecast data, and the predicted agricultural water demand is calculated based on the predicted water shortage of crop irrigation and the future rainfall data of the irrigation area.

[0080] It is understandable that even if the irrigation area is in a drought period, in order to achieve a comprehensive and accurate water demand forecast, the rainfall in the irrigation area still needs to be taken into consideration. The future soil moisture content is obtained by subtracting the cumulative evaporation from the current soil moisture content. The future soil moisture content, combined with the relatively fixed average bulk density of the soil at the depth and the water holding capacity of the soil at the depth, can be used to calculate the predicted water shortage for crop irrigation. The predicted future rainfall in the irrigation area can be supplemented with the predicted water shortage for crop irrigation to obtain the specific value of the predicted agricultural water demand.

[0081] Step S20: obtaining the total number of non-agricultural water users in the irrigation area and a plurality of historical non-agricultural water use data, and extracting a plurality of periodic characteristic parameters from the plurality of historical non-agricultural water use data;

[0082] Preferably, non-agricultural water use includes domestic water use, water use by water plants and factories, etc. The water use data of the non-agricultural water users roughly changes periodically over time. For example, domestic water use has certain rules according to the year, month, day or season, and factory production has off-season and peak season, etc.

[0083] Specifically, the step S20 includes:

[0084] S210: standardizing a plurality of the historical non-agricultural water use data into a plurality of water use data to be extracted;

[0085] Preferably, the scale of the data is unified to prevent a certain feature parameter from affecting the prediction result due to its large magnitude during the subsequent model training process.

[0086] S220: Based on the characteristics of the plurality of non-agricultural water users, an extraction module is constructed, and the plurality of water use data to be extracted is input into the extraction module to obtain a plurality of periodic characteristic parameters.

[0087] Preferably, an LSTM (Long Short-Term Memory) network is used, i.e., a long short-term memory network, and the extraction module is constructed based on an LSTM memory unit layer.

[0088] Step S30: constructing a plurality of prediction modules and a plurality of discarding layers based on the total quantity, and associating the plurality of prediction modules with the plurality of discarding layers to form a plurality of prediction models, and training the plurality of prediction models based on the plurality of periodic characteristic parameters to obtain non-agricultural predicted water demand;

[0089] Specifically, in step S30, the number of the prediction modules and the number of the discarded layers are both three times the total number, the discard rate of the discarded layer is 0.3, and the number of the prediction models is equal to the total number.

[0090] Preferably, the prediction model includes three layers, each layer is constructed by connecting an LSTM module to the discard layer, the number of hidden units of the LSTM module in the first layer is 150, the number of hidden units of the LSTM module in the second layer is 100, and the number of hidden units of the LSTM module in the third layer is 100. Furthermore, the prediction model is also connected to a fully connected layer and uses a sigmoid activation function to output predictions. The prediction model also includes a loss function, and each training round aims to minimize the loss function.

[0091] Step S40: Acquire water and soil data between the reservoir group and the irrigation area, and construct an evolution model;

[0092] Preferably, the water supply and demand topological relationship between the reservoir group and the irrigation area, the topography, land use, hydrological conditions, etc. constitute the water and soil data.

[0093] Step S50: Obtaining rainfall and the discharge flow process of the reservoir group, and inputting them into the evolution model to calculate the water flow process at the head of the irrigation area;

[0094] Preferably, the rainfall represents the rainfall between the upstream reservoir group and the irrigation area, and the reservoir group discharge flow process is continuous data constituted by historical and current reservoir group discharge flow related data and time association. According to the reservoir group discharge flow process, discrete discharge plans and the discharge flow in the plans can be extracted.

[0095] Specifically, the evolution model includes a hydrological sub-model and a river flow evolution sub-model, and step S50 includes:

[0096] S510: Inputting the rainfall into the hydrological sub-model to obtain the runoff from the reservoir group to the head of the irrigation area;

[0097] Preferably, the grid rainfall data in the external meteorological forecast model is accessed to obtain the rainfall in the required area. The hydrological sub-model can be established based on the Sanshuiyuan Xin'anjiang model, the SWAT model, the VIC model, the SCS-CN model, etc. Furthermore, in this embodiment, the Sanshuiyuan Xin'anjiang model is used as the basis to calculate the runoff in the interval and quantify the pathway factors between the water source and the irrigation area.

[0098] S520: extracting the reservoir group discharge plan from the reservoir group discharge process, taking the reservoir group discharge plan and the interval flow production and confluence as boundary conditions of the river flow evolution sub-model, and calculating the inflow flow process at the head of the irrigation area.

[0099] Preferably, the river flow evolution sub-model is established based on the Muskingum model. Specifically, the parameters of the river flow evolution sub-model are calibrated according to the historical flow monitoring data of the hydrological station, the historical discharge data of the reservoir, the historical rainfall monitoring data, and the coupling hydrological model.

[0100] Step S60: based on the water flow process at the canal head of the irrigation area, calculating the total water flow at the canal head of the irrigation area, and based on the agricultural predicted water demand, the non-agricultural predicted water demand and the total water flow, calculating the water resource surplus of the irrigation area;

[0101] It can be understood that the amount of water replenishment required by the irrigation area is optimized according to the water resource surplus of the irrigation area itself. The larger the surplus, the less water replenishment is required.

[0102] Step S70: Based on the evolution model and the genetic algorithm, a scheme optimization model is established, and based on the discharge flow process of the reservoir group and the water resource surplus, the objective function in the scheme optimization model is calculated to screen several reservoir group discharge scheme samples to obtain the final reservoir group discharge scheme, and supply water to the irrigation area based on the final reservoir group discharge scheme.

[0103] Preferably, in the scheme optimization model, the decision variable is the discharge flow of a certain reservoir at a certain point in time. Considering the water resource surplus and the reservoir operating cost, a weight factor is assigned to make a trade-off and facilitate the subsequent adjustment of the weight factor. The goal is to minimize the weighted value of the water resource surplus and the reservoir operating cost, that is, the objective function is calculated with the lowest reservoir operating cost as the goal on the basis of fully considering the water resource surplus; according to the characteristics of the genetic algorithm, the scheme optimization model randomly generates a series of discharge schemes for the reservoir group as the initial population, and the scheme includes different reservoir discharge flow settings as the basic samples of the genetic algorithm. According to the discharge flow process of the reservoir group and the water resource surplus, more samples are input into the scheme optimization model to form more discharge schemes for the reservoir group to form the current population, and the value of the objective function is used as the sample fitness. Better sample individuals are selected from the current population and retained in the next generation population. New individuals are generated by pairing and crossover operations of the samples, and then random mutation operations are performed on the new individuals, and iterative operations are performed to finally obtain the optimal scheme.

[0104] Specifically, the reservoir group includes several reservoirs, and the formula of the objective function in step S70 is:

[0105]

[0106] in, is the objective function, is the weight function of water resource surplus and reservoir group dispatching operation cost, is the first Reservoir Hourly discharge flow, , is the length of the forecast period in days, is the first weight factor, For the future The water resource surplus of the irrigation area per day, is the second weight factor, For the future The operation cost of the reservoir group dispatching per day, The formula is:

[0107]

[0108] in, , is the total number of reservoirs, , For the future Day's The operation cost of a reservoir is The formula is:

[0109]

[0110] in, is the first Reservoir Hourly discharge flow.

[0111] Preferably, the first weight factor is 0.7, and the second weight factor is 0.3.

[0112] In the step S70, after the step of calculating the objective function in the solution optimization model, the following step is further included:

[0113] S710: Obtaining the water storage capacity and inflow of the reservoir, and extracting the reservoir discharge flow from the discharge flow process of the reservoir group to form a water balance constraint;

[0114] The reservoir water demand, the reservoir inflow and the reservoir discharge at the beginning and end of a certain period are respectively established, and a constraint equation is established based on the relationship between the three.

[0115] S720: Obtain the lowest water level and the highest water level of the reservoir to form a reservoir water level constraint;

[0116] It can be understood that the water level of a certain reservoir in a certain period of time is greater than the lowest water level of the reservoir and less than the highest water level of the reservoir.

[0117] S730: Obtaining the maximum discharge capacity of the reservoir to form a reservoir discharge capacity constraint;

[0118] It can be understood that the outflow rate in a certain period of time is a non-negative number and is less than or equal to the maximum discharge capacity of the reservoir.

[0119] S740: The water balance constraint, the reservoir water level constraint and the reservoir discharge capacity constraint constitute constraint conditions, and the constraint conditions are added to the solution optimization model.

[0120] The constraint condition imposes a limited range on the formed reservoir group discharge plan, which is used in the iterative optimization process of the solution optimization model. It can be understood that the water supply inversion method of the irrigation area water source during the drought period clarifies the demand for water replenishment in the water source and provides sufficient data support.

[0121] See also Figure 2 In another embodiment of the present invention, a water supply inversion system for a water source area in a drought period is applied to the water supply inversion method for a water source area in a drought period described in the above embodiment. The system comprises:

[0122] The first prediction module 10 is used to obtain soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, obtain weather forecast data, and calculate the agricultural predicted water demand based on the soil moisture data, the crop characteristic data, the soil bulk density data and the weather forecast data;

[0123] The first prediction module 10 comprises:

[0124] The first unit is used to calculate the crop irrigation water shortage based on the soil moisture data, the crop characteristic data and the soil bulk density data;

[0125] The first unit is specifically used to extract the crop root activity layer depth from the crop characteristic data, and determine the planned soil moist layer depth based on the crop root activity layer depth;

[0126] Extracting soil water holding capacity and current soil water content from the soil moisture data;

[0127] Based on the soil bulk density data, calculating the average soil bulk density;

[0128] Calculating the water shortage for crop irrigation based on the planned soil moist layer depth, the soil water holding capacity, the current soil moisture content and the average soil bulk density;

[0129] The second unit is used for predicting the potential evapotranspiration of crops using the Thornthwaite model based on the meteorological forecast data;

[0130] The third unit is used to calculate the predicted agricultural water demand based on the crop irrigation water shortage, the crop potential evapotranspiration and the meteorological forecast data;

[0131] The third unit is specifically used to calculate the future soil moisture content based on the crop potential evapotranspiration and the current soil moisture content, and update the crop irrigation water shortage to the crop irrigation predicted water shortage according to the crop irrigation water shortage and the future soil moisture content;

[0132] The future rainfall data of the irrigation area is extracted from the weather forecast data, and the predicted agricultural water demand is calculated based on the predicted water shortage of crop irrigation and the future rainfall data of the irrigation area.

[0133] An extraction module 20 is used to obtain the total number of non-agricultural water users in the irrigation area and a plurality of historical non-agricultural water use data, and extract a plurality of periodic characteristic parameters from the plurality of historical non-agricultural water use data;

[0134] The extraction module 20 comprises:

[0135] A fourth unit is used to standardize a plurality of the historical non-agricultural water use data into a plurality of water use data to be extracted;

[0136] The fifth unit is used to construct an extraction module based on the characteristics of the plurality of non-agricultural water users, and input the plurality of water use data to be extracted into the extraction module to obtain a plurality of periodic characteristic parameters.

[0137] A second prediction module 30 is used to construct a plurality of prediction modules and a plurality of discarding layers based on the total quantity, and associate the plurality of prediction modules with the plurality of discarding layers to form a plurality of prediction models, and train the plurality of prediction models based on the plurality of periodic characteristic parameters to obtain non-agricultural predicted water demand;

[0138] Preferably, in the second prediction module 30, the number of the prediction modules and the number of the discarded layers are both three times the total number, the discard rate of the discarded layer is 0.3, and the number of the prediction models is equal to the total number.

[0139] A construction module 40 is used to obtain water and soil data between the reservoir group and the irrigation area and construct an evolution model;

[0140] The flow module 50 is used to obtain the rainfall and the discharge flow process of the reservoir group, and input them into the evolution model to calculate the water flow process at the head of the irrigation area;

[0141] The flow module 50 includes:

[0142] The sixth unit is used to input the rainfall into the hydrological sub-model to obtain the flow generation and convergence of the interval from the reservoir group to the head of the irrigation area;

[0143] The seventh unit is used to extract the reservoir group discharge plan from the discharge process of the reservoir group, use the reservoir group discharge plan and the interval flow production and confluence as the boundary conditions of the river flow evolution sub-model, and calculate the inflow flow process at the head of the irrigation area.

[0144] A surplus module 60 is used to calculate the total amount of water inflow at the head of the irrigation area based on the water inflow flow process at the head of the irrigation area, and calculate the water resource surplus of the irrigation area based on the agricultural predicted water demand, the non-agricultural predicted water demand and the total amount of water inflow;

[0145] The optimization module 70 is used to establish a scheme optimization model based on the evolution model and the genetic algorithm, and calculate the objective function in the scheme optimization model based on the discharge flow process of the reservoir group and the water resource surplus, so as to screen several reservoir group discharge plan samples to obtain the final reservoir group discharge plan, and supply water to the irrigation area based on the final reservoir group discharge plan.

[0146] Preferably, in the optimization module 70, the reservoir group includes several reservoirs, and the formula of the objective function in the optimization module 70 is:

[0147]

[0148] in, is the objective function, is the weight function of water resource surplus and reservoir group dispatching operation cost, is the first Reservoir Hourly discharge flow, , is the length of the forecast period in days, is the first weight factor, For the future The water resource surplus of the irrigation area per day, is the second weight factor, For the future The operation cost of the reservoir group dispatching per day, The formula is:

[0149]

[0150] in, , is the total number of reservoirs, , For the future Day's The operation cost of a reservoir is The formula is:

[0151]

[0152] in, is the first Reservoir Hourly discharge flow.

[0153] The optimization module 70 includes:

[0154] The eighth unit is used to obtain the water storage capacity and the inflow of the reservoir, and extract the reservoir discharge flow from the discharge flow process of the reservoir group to form a water balance constraint;

[0155] The ninth unit is used to obtain the minimum water level and the maximum water level of the reservoir to form the reservoir water level constraint;

[0156] The tenth unit is used to obtain the maximum discharge capacity of the reservoir to form the reservoir discharge capacity constraint;

[0157] The eleventh unit is used for the water balance constraint, the reservoir water level constraint and the reservoir discharge capacity constraint to constitute constraint conditions, and the constraint conditions are added to the solution optimization model.

[0158] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0159] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for inverting water supply from a water source in an irrigation area during a drought, characterized in that: The steps include: Acquire soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, acquire weather forecast data, and calculate agricultural predicted water demand based on the soil moisture data, crop characteristic data, soil bulk density data and weather forecast data; Obtaining the total number of non-agricultural water users in the irrigation area and a number of historical non-agricultural water use data, and extracting a number of periodic characteristic parameters from the historical non-agricultural water use data; Based on the total quantity, a plurality of prediction modules and a plurality of discarding layers are constructed, and a plurality of the prediction modules are associated with a plurality of the discarding layers to form a plurality of prediction models, and a plurality of the prediction models are trained based on a plurality of the periodic characteristic parameters to obtain non-agricultural predicted water demand; Acquire water and soil data between the reservoir group and the irrigation area, and construct an evolution model; Obtaining rainfall and the discharge flow process of the reservoir group, and inputting them into the evolution model to calculate the water flow process at the head of the irrigation area; Based on the water flow process at the canal head of the irrigation area, the total water flow at the canal head of the irrigation area is calculated, and based on the agricultural predicted water demand, the non-agricultural predicted water demand and the total water flow, the water resource surplus of the irrigation area is calculated; Based on the evolutionary model and the genetic algorithm, a scheme optimization model is established, and based on the discharge flow process of the reservoir group and the water resource surplus, the objective function in the scheme optimization model is calculated to screen several reservoir group discharge scheme samples to obtain the final reservoir group discharge scheme, and water is supplied to the irrigation area based on the final reservoir group discharge scheme.

2. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 1 is characterized in that: The step of obtaining soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, obtaining weather forecast data, and calculating the predicted agricultural water demand based on the soil moisture data, the crop characteristic data, the soil bulk density data and the weather forecast data comprises: Calculating the amount of water shortage for crop irrigation based on the soil moisture data, the crop characteristic data and the soil bulk density data; Based on the weather forecast data, the Thornthwaite model is used to predict the potential evapotranspiration of crops; The predicted agricultural water demand is calculated based on the crop irrigation water shortage, the crop potential evapotranspiration and the weather forecast data.

3. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 2 is characterized in that: The step of calculating the crop irrigation water shortage based on the soil moisture data, the crop characteristic data and the soil bulk density data comprises: Extracting the crop root activity layer depth from the crop characteristic data, and determining the planned soil moist layer depth based on the crop root activity layer depth; Extracting soil water holding capacity and current soil water content from the soil moisture data; Based on the soil bulk density data, calculating the average soil bulk density; The water shortage for crop irrigation is calculated based on the planned soil moistening layer depth, the soil water holding capacity, the current soil moisture content and the average soil bulk density.

4. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 3 is characterized in that: The step of calculating the predicted agricultural water demand based on the crop irrigation water shortage, the crop potential evapotranspiration and the meteorological forecast data comprises: Calculating the future soil moisture content based on the crop potential evapotranspiration and the current soil moisture content, and updating the crop irrigation water shortage to the crop irrigation predicted water shortage according to the crop irrigation water shortage and the future soil moisture content; The future rainfall data of the irrigation area is extracted from the weather forecast data, and the predicted agricultural water demand is calculated based on the predicted water shortage of crop irrigation and the future rainfall data of the irrigation area.

5. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 1 is characterized in that: The step of extracting a plurality of periodic characteristic parameters from a plurality of historical non-agricultural water use data comprises: Standardizing a plurality of the historical non-agricultural water use data into a plurality of water use data to be extracted; Based on the characteristics of the plurality of non-agricultural water users, an extraction module is constructed, and the plurality of water use data to be extracted are input into the extraction module to obtain a plurality of periodic characteristic parameters.

6. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 1 is characterized in that: The number of the prediction modules and the number of the discarded layers are both three times the total number, the discard rate of the discarded layer is 0.3, and the number of the prediction models is equal to the total number.

7. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 1 is characterized in that: The evolution model includes a hydrological sub-model and a river flow evolution sub-model. The steps of inputting the evolution model to calculate the water flow process at the head of the irrigation area include: Inputting the rainfall into the hydrological sub-model to obtain the flow generation and convergence between the reservoir group and the head of the irrigation area; The discharge scheme of the reservoir group is extracted from the discharge process of the reservoir group, and the discharge scheme of the reservoir group and the flow generation and confluence of the interval are used as boundary conditions of the river flow evolution sub-model to calculate the inflow flow process at the head of the irrigation area.

8. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 1 is characterized in that: The reservoir group includes several reservoirs, and the formula of the objective function is: in, is the objective function, is the weight function of water resource surplus and reservoir group dispatching operation cost, is the first Reservoir Hourly discharge flow, , is the length of the forecast period in days, is the first weight factor, For the future The water resource surplus of the irrigation area per day, is the second weight factor, For the future The operation cost of reservoir group dispatching per day, The formula is: in, , is the total number of reservoirs, , For the future Day's The operation cost of a reservoir is The formula is: in, is the first Reservoir Hourly discharge flow.

9. The method for inverting water supply from a water source in an irrigation area during a drought period according to claim 8, characterized in that: After the step of calculating the objective function in the solution optimization model, the method further includes: Obtaining the water storage capacity and inflow of the reservoir, and extracting the reservoir discharge from the discharge process of the reservoir group to form a water balance constraint; Obtain the minimum water level and the maximum water level of the reservoir to form the reservoir water level constraint; Obtain the maximum discharge capacity of the reservoir to form the reservoir discharge capacity constraint; The water balance constraint, the reservoir water level constraint and the reservoir discharge capacity constraint constitute constraint conditions, and the constraint conditions are added to the solution optimization model.

10. A water supply inversion system for a water source area in a drought period, applied to the water supply inversion method for a water source area in a drought period as claimed in any one of claims 1 to 9, characterized in that: The system comprises: The first prediction module is used to obtain soil moisture data, crop characteristic data and soil bulk density data in the irrigation area, obtain weather forecast data, and calculate the agricultural predicted water demand based on the soil moisture data, the crop characteristic data, the soil bulk density data and the weather forecast data; An extraction module, used to obtain the total number of non-agricultural water users in the irrigation area and a plurality of historical non-agricultural water use data, and extract a plurality of periodic characteristic parameters from the plurality of historical non-agricultural water use data; A second prediction module is used to construct a plurality of prediction modules and a plurality of discarding layers based on the total quantity, and associate the plurality of prediction modules with the plurality of discarding layers to form a plurality of prediction models, and train the plurality of prediction models based on the plurality of periodic characteristic parameters to obtain non-agricultural predicted water demand; A construction module is used to obtain water and soil data between the reservoir group and the irrigation area and construct an evolution model; A flow module, used for obtaining rainfall and the discharge flow process of the reservoir group, and inputting the flow into the evolution model to calculate the flow process of the water flow at the head of the irrigation area; A surplus module, used to calculate the total amount of water inflow at the head of the irrigation area based on the water inflow flow process at the head of the irrigation area, and calculate the water resource surplus of the irrigation area based on the agricultural predicted water demand, the non-agricultural predicted water demand and the total amount of water inflow; An optimization module is used to establish a scheme optimization model based on the evolution model and the genetic algorithm, and calculate the objective function in the scheme optimization model based on the discharge flow process of the reservoir group and the water resource surplus, so as to screen several reservoir group discharge plan samples to obtain the final reservoir group discharge plan, and supply water to the irrigation area based on the final reservoir group discharge plan.

Images