Method and system for determining scale layout of water network irrigation projects in agricultural and pastoral areas

Abstract

The present invention discloses a method and system for determining the scale layout of water network irrigation projects in agricultural and pastoral areas. The method collects agricultural and pastoral area data, grids the agricultural and pastoral areas, constructs a terrain feature matrix, calculates the rainfall of each grid, calculates the evapotranspiration value, and performs water and soil balance calculations. Several drought centers are extracted and the agricultural and pastoral areas are divided into several sub-areas. The water inflow of each sub-area is calculated, a water layer distribution map is drawn, the water intake is determined, and a water source project layout plan is constructed for each sub-area. The water outlet of the water source project in each sub-area is extracted, and the irrigation system is determined based on the irrigation area terrain data. The drainage project is constructed to obtain the irrigation project layout plan for each sub-area. An evaluation index system and an economic evaluation model are constructed to calculate the comprehensive benefit score of the water network irrigation project layout plan. The plan with the highest score is the scale layout plan for the water network irrigation project in the agricultural and pastoral areas. The present invention improves the efficiency of water resource utilization and achieves the rational allocation and sustainable utilization of water resources in agricultural and pastoral areas.

Description

Technical Field

[0001] The invention relates to a method for determining the scale layout of a water network irrigation area project in an agricultural and pastoral area. Background Art

[0002] The scale layout of water network irrigation projects is crucial to the sustainable development of agriculture and animal husbandry. A reasonable layout of water network irrigation projects can effectively allocate water resources, improve irrigation efficiency, promote increased production and income in agriculture and animal husbandry, and protect the ecological environment. However, the existing methods for determining the scale layout of water network irrigation projects in agricultural and pastoral areas have many shortcomings.

[0003] On the one hand, when calculating regional rainfall and evapotranspiration values, traditional methods often use simple statistical or empirical formulas, and do not fully consider the influence of complex factors such as terrain, resulting in low accuracy of calculation results and difficulty in accurately reflecting the actual water resource situation; on the other hand, when determining the layout of water source projects, irrigation systems and drainage projects, there is a lack of systematic and comprehensive planning, and the actual needs and characteristics of agricultural and pastoral areas are not fully taken into account, resulting in unreasonable project layout and low water resource utilization efficiency, which cannot meet the growing water demand in agricultural and pastoral areas. In addition, when evaluating project layout plans, the existing methods have a single evaluation indicator and fail to fully consider the economic, social and ecological benefits, making it difficult to select the optimal project scale layout plan. Therefore, there is an urgent need for a scientific, accurate and comprehensive method and system for determining the scale layout of water network irrigation projects in agricultural and pastoral areas.

[0004] The present invention proposes a method and system for determining the scale layout of water network irrigation projects in agricultural and pastoral areas, which solves the above-mentioned existing problems, improves the efficiency of water resource utilization, and realizes the rational allocation and sustainable utilization of water resources in agricultural and pastoral areas. Summary of the Invention

[0005] The invention aims to provide a method for determining the scale and layout of water network irrigation projects in agricultural and pastoral areas to solve the above-mentioned problems existing in the prior art. On the other hand, a system for determining the scale and layout of water network irrigation projects in agricultural and pastoral areas is provided.

[0006] Technical solution: A method for determining the scale and layout of water network irrigation projects in agricultural and pastoral areas includes the following steps:

[0007] Step S1: Collect agricultural and pastoral area data, grid the agricultural and pastoral areas, construct a terrain feature matrix, calculate the rainfall of each grid, use a pre-built long-short-term memory model to calculate the evapotranspiration value, perform soil and water balance calculations, extract several drought centers, and divide the agricultural and pastoral areas into several sub-areas;

[0008] Step S2: Calculate the water inflow of each sub-region, draw a water layer distribution map, calculate the water quality rate based on the water source water volume data and water demand, determine the water intake, and construct a water source project layout plan for each sub-region based on the spatial distribution of the drought center;

[0009] Step S3: Extract the water outlet of each sub-region's water source project, combine it with the irrigation area's topographic data, determine the irrigation system, construct a drainage project based on the rainstorm intensity data and topographic water catchment data of each sub-region, and obtain the irrigation project layout plan for each sub-region;

[0010] Step S4: Construct an evaluation index system, calculate the index values ​​of the water network irrigation project layout plan for each sub-region, input them into the pre-built economic evaluation model, calculate the corresponding comprehensive benefit score, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

[0011] According to one aspect of the present application, step S1 further comprises:

[0012] Step S11, collecting agricultural and pastoral area data, including: agricultural and pastoral area digital elevation data, meteorological data, rainfall station observation data, crop planting structure data, and livestock breeding scale data;

[0013] Step S12: gridding the study area based on the agricultural and pastoral area terrain data, extracting agricultural and pastoral area digital elevation data and rainfall station observation data, and constructing an agricultural and pastoral area terrain feature matrix;

[0014] Step S13: Calculate the terrain similarity between each grid and each rainfall station using the Euclidean distance improved by cosine similarity, and optimize the inverse distance weight formula based on the terrain similarity to obtain a hybrid weight function. Use the hybrid weight function to perform weighted averaging on each grid to obtain the corresponding rainfall.

[0015] Step S14: Collect historical data of agricultural and pastoral areas to calculate historical potential evapotranspiration values ​​of agricultural and pastoral areas, and train a pre-built long-short-term memory model together with the historical actual evapotranspiration values ​​of agricultural and pastoral areas. Extract the agricultural and pastoral area data as input to the trained long-short-term memory model to calculate the actual evapotranspiration values ​​of agricultural and pastoral areas.

[0016] Step S15: Calculate the historical available water volume in the agricultural and pastoral areas based on the historical rainfall and historical potential evapotranspiration values ​​in the agricultural and pastoral areas, perform soil and water balance calculations on the agricultural and pastoral areas based on the agricultural and pastoral area data, obtain the historical water demand in the agricultural and pastoral areas, calculate the historical water demand of each grid in the agricultural and pastoral areas, extract several drought centers, and divide the agricultural and pastoral areas into several sub-areas.

[0017] According to one aspect of the present application, step S12 is further as follows:

[0018] Step S12a, extracting the agricultural and pastoral area terrain data, setting the grid resolution to grid the agricultural and pastoral area, and obtaining the agricultural and pastoral area terrain grid;

[0019] Step S12b: Based on the grid resolution of the agricultural and pastoral terrain, the rainfall station data is converted into a spatial distribution grid using the inverse distance weighted method;

[0020] Step S12c: Integrate the agricultural and pastoral area terrain grid and the rainfall spatial distribution grid to obtain the agricultural and pastoral area terrain feature matrix.

[0021] According to one aspect of the present application, step S15 is further as follows:

[0022] Step S15a, extracting historical rainfall and historical potential evapotranspiration values ​​in the agricultural and pastoral areas, and calculating the historical available water volume in the pastoral areas;

[0023] Step S15b: extract the crop type, irrigation method, soil characteristics, crop water requirement coefficient and crop growth cycle in the agricultural and pastoral areas, calculate the crop water requirement at each time point in each grid in the agricultural and pastoral areas, summarize the living and ecological water requirements, and obtain the historical water requirements of the agricultural and pastoral areas;

[0024] Step S15c: Extract water demand data for each grid at each time point in the agricultural and pastoral areas, map water demand to color and draw a drought distribution map using the grid as a unit, with the color corresponding to the water demand from light to dark from small to large. Superimpose the distribution maps at each time point, calculate the total and average water demand of each grid, extract grids whose total and average water demand are both greater than a threshold, and divide the connected grids into the same area to obtain several drought centers;

[0025] Step S15d: Based on the spatial distribution of drought centers, the agricultural and pastoral areas are divided into several sub-areas using Thiessen polygons, each of which contains a drought center.

[0026] According to one aspect of the present application, step S2 further comprises:

[0027] Step S21: Collecting hydrological station detection data and using cross-sectional flow calculation method to collect water flow data at different frequencies;

[0028] Step S22: collecting hydrological data and water level dynamic changes, detecting water quality parameters, water quality indicators and water quantity parameters, and drawing a water layer distribution map;

[0029] Step S23: Calculate the water quality rate based on the water source water quantity data and the water demand, determine the feasibility of water extraction based on the elevation difference between the water source water level and the water intake point in the irrigation area, and select the water intake;

[0030] Step S24: construct surface water source engineering plans and groundwater source engineering plans based on the spatial distribution of drought centers, and combine them to obtain water source engineering layout plans for each sub-region.

[0031] According to one aspect of the present application, step S24 is further as follows:

[0032] Step S24a: Collect groundwater level monitoring data and river and lake water level data for each sub-region, draw a water level contour map based on water demand, extract the coordinates of the water level contour lines, and calculate the slope of each contour line;

[0033] Step S24b: Set an initial buffer distance, generate a circular initial buffer zone with the drought center as the center, modify the initial buffer zone based on the density of water level contour lines, set a slope threshold, and divide the buffer zone into a core buffer zone and a secondary buffer zone based on the calculated contour line slopes;

[0034] Step S24c: construct surface water source engineering schemes and groundwater source engineering schemes for each sub-region for the core buffer zone and the secondary buffer zone, input the pre-constructed water resources joint scheduling model, and solve the model to obtain the water source engineering layout scheme for each sub-region.

[0035] According to one aspect of the present application, step S3 is further:

[0036] Step S31: collecting the terrain slope of the irrigation area, the soil permeability coefficient, the distribution of crop planting areas, and the location of the water outlet of the water source project;

[0037] Step S32: Select an irrigation system based on the terrain slope, and calculate the pipe diameter, dripper spacing, channel cross-sectional dimensions, and pump station head;

[0038] Step S33: construct drainage projects based on the rainstorm intensity data and topographic water catchment data of each sub-region, and obtain irrigation project layout plans for each sub-region.

[0039] According to one aspect of the present application, step S4 is further:

[0040] Step S41: constructing an evaluation index system, including economic value index, social benefit index and ecological benefit index;

[0041] Step S42: Calculate the index value of the water network irrigation project layout plan for each sub-region respectively;

[0042] Step S43: construct an economic evaluation model, extract the index values ​​of the water network irrigation project layout plan of each sub-region as the model input, calculate the comprehensive benefit score of the water network irrigation project layout plan of each sub-region, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

[0043] According to one aspect of the present application, step S42 is further as follows:

[0044] Step S42a: Calculate economic benefit indicators using a dynamic analysis method, including net present value, internal rate of return, and payback period;

[0045] Step S42b: Calculate social benefit indicators using the analytic hierarchy process, including: quality of life, employment opportunities, and social stability;

[0046] Step S42c: Calculate the ecological benefit index using the ecological environment quality index method.

[0047] According to one aspect of the present application, step S43 is further as follows:

[0048] Step S43a: Construct a multi-level comprehensive evaluation model, including a target layer, a criterion layer, and an indicator layer. The target layer is the comprehensive benefits of the scale layout plan of the agricultural and pastoral water network irrigation project. The criterion layer includes economic benefits, social benefits, and ecological benefits. The indicator layer is further subdivided according to the criterion layer.

[0049] Step S43b: perform pairwise comparison and scoring of the importance of indicators based on the 1-9 scale method, construct a judgment matrix, calculate the eigenvector and maximum eigenroot of the judgment matrix, perform consistency test, determine the weight of each indicator and configure a multi-level comprehensive evaluation model;

[0050] Step S43c: extract the index values ​​of the water network irrigation project layout plan of each sub-region as the input of the multi-level comprehensive evaluation model, calculate the comprehensive benefit score of the water network irrigation project layout plan of each sub-region, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

[0051] According to another aspect of the present application, a system for determining the scale layout of water network irrigation projects in agricultural and pastoral areas is provided, comprising:

[0052] at least one processor; and

[0053] a memory communicatively connected to at least one of the processors; wherein,

[0054] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the method for determining the scale layout of water network irrigation projects in agricultural and pastoral areas as described in any of the above technical solutions.

[0055] Beneficial effects: A method for determining the scale layout of water network irrigation projects in agricultural and pastoral areas is adopted. Relevant data of agricultural and pastoral areas are collected and analyzed through scientific methods to construct a reasonable project layout plan. The optimal scale layout plan of water network irrigation projects in agricultural and pastoral areas is determined through a comprehensive evaluation index system and economic evaluation model. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart of the present invention.

[0057] Figure 2 It is a flow chart of step S1 of the present invention.

[0058] Figure 3 It is a flow chart of step S2 of the present invention.

[0059] Figure 4 It is a flow chart of step S3 of the present invention.

[0060] Figure 5 It is a flow chart of step S4 of the present invention. DETAILED DESCRIPTION

[0061] like Figure 1 According to one aspect of the present application, a method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area is provided, which is characterized by comprising the following steps:

[0062] Step S1: Collect agricultural and pastoral area data, grid the agricultural and pastoral areas, construct a terrain feature matrix, calculate the rainfall of each grid, use a pre-built long-short-term memory model to calculate the evapotranspiration value, perform soil and water balance calculations, extract several drought centers, and divide the agricultural and pastoral areas into several sub-areas;

[0063] Step S2: Calculate the water inflow of each sub-region, draw a water layer distribution map, calculate the water quality rate based on the water source water volume data and water demand, determine the water intake, and construct a water source project layout plan for each sub-region based on the spatial distribution of the drought center;

[0064] Step S3: Extract the water outlet of each sub-region's water source project, combine it with the irrigation area's topographic data, determine the irrigation system, construct a drainage project based on the rainstorm intensity data and topographic water catchment data of each sub-region, and obtain the irrigation project layout plan for each sub-region;

[0065] Step S4: Construct an evaluation index system, calculate the index values ​​of the water network irrigation project layout plan for each sub-region, input them into the pre-built economic evaluation model, calculate the corresponding comprehensive benefit score, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

[0066] First, digital elevation data, meteorological data, rainfall station observation data, crop planting structure, and livestock breeding scale data from agricultural and pastoral areas were collected. The agricultural and pastoral areas were gridded and a terrain feature matrix was constructed. The terrain similarity between each grid and the rainfall station was calculated using the Euclidean distance improved by cosine similarity. The inverse distance weight formula was optimized to obtain a hybrid weight function, thereby accurately calculating the rainfall in each grid. At the same time, a long-term and short-term memory model was constructed. The historical potential evapotranspiration value was calculated based on historical data, and the model was trained together with the historical true evapotranspiration value. The current data was input to obtain the true evapotranspiration value. The available water was calculated based on the rainfall and evapotranspiration values. The water and soil balance was calculated in combination with other agricultural and pastoral data to obtain the water demand and water shortage. The drought center was identified and the agricultural and pastoral areas were divided based on the drought center to obtain several sub-regions.

[0067] Next, we collected data from hydrological stations and used the cross-sectional flow calculation method to obtain water inflow data at different frequencies. We also collected hydrological and water level dynamics as well as water quality and quantity parameters, mapped the water layer distribution, calculated the water quality rate based on the source water volume and water demand, and determined the water intake based on the elevation difference between the source water level and the irrigation area intake point. We then constructed separate surface water and groundwater source engineering plans. Using the water resources joint scheduling model, we derived the layout plans for water source engineering in each sub-region, achieving a rational allocation plan for water resources.

[0068] Then, data on the terrain slope and soil permeability coefficient of the irrigation area are collected. Based on the terrain slope, appropriate irrigation systems are selected and relevant parameters are calculated. Combined with the rainstorm intensity and topographic water catchment data, drainage projects are constructed to form a layout plan for irrigation projects in each sub-region, ensuring the scientific rationality of irrigation and drainage.

[0069] Finally, an evaluation index system covering economic, social and ecological benefits is constructed, and the index values ​​are calculated using dynamic analysis and hierarchical analysis methods. A multi-level comprehensive evaluation model is constructed to determine the index weights. The index values ​​of each plan are input to calculate the comprehensive benefit score, and the plan with the highest score is selected as the scale layout plan for water network irrigation projects in agricultural and pastoral areas.

[0070] like Figure 2 As shown, according to one aspect of the present application, the step S1 is further:

[0071] Step S11, collecting agricultural and pastoral area data, including: agricultural and pastoral area digital elevation data, meteorological data, rainfall station observation data, crop planting structure data, and livestock breeding scale data;

[0072] Step S12: gridding the study area based on the agricultural and pastoral area terrain data, extracting agricultural and pastoral area digital elevation data and rainfall station observation data, and constructing an agricultural and pastoral area terrain feature matrix;

[0073] Step S13: Calculate the terrain similarity between each grid and each rainfall station using the Euclidean distance improved by cosine similarity, and optimize the inverse distance weight formula based on the terrain similarity to obtain a hybrid weight function. Use the hybrid weight function to perform weighted averaging on each grid to obtain the corresponding rainfall.

[0074] In one embodiment, step S13 is specifically as follows:

[0075] Step S13a: extracting multidimensional terrain features of each grid and rainfall station based on the digital elevation data, constructing terrain feature vectors, calculating the directional similarity between vectors using cosine similarity, and calculating the spatial distance between vectors using Euclidean distance, and fusing the similarity and spatial distance to obtain the terrain similarity between vectors, i.e., the terrain similarity of each grid and each rainfall station;

[0076] Preprocess the digital elevation data of the study area to extract slope, aspect, terrain moisture index, and terrain position index, and construct the terrain feature matrix: F=[f1,f2,...,fn] T ;

[0077] Among them, fi represents the i-th terrain feature layer;

[0078] Calculate the terrain characteristic vectors of the interpolation point p and each rainfall station s:

[0079] Vp=[s p ,a p ,tpi p ,twi p ];Vs=[s s ,a s ,tpi s ,twi s ];

[0080] Where s represents slope, a represents aspect, tpi represents terrain position index, and twi represents terrain wetness index;

[0081] The cosine similarity is combined with the Euclidean distance to construct a comprehensive similarity index: S = α·cosθ+(1-α)·exp(-β·dmaxd); where θ is the angle between the feature vectors, d is the Euclidean distance, and α and β are weight coefficients.

[0082] Step S13b: Fusing the terrain similarity with the inverse distance weight formula to obtain an optimized inverse distance weight formula, and using an adaptive particle swarm algorithm to dynamically determine the optimization parameters to obtain a hybrid weight function;

[0083] Adjusting traditional inverse distance weighting based on terrain similarity:

[0084] Wi=d i -pm ·exp(-γ·(1-Si)); or Wi=(1 / d i pm )×exp(-γ×(1-Si));

[0085] Among them, di is the distance, pm is the distance power parameter, Si is the terrain similarity, and γ is the terrain influence coefficient;

[0086] Dynamically determine the optimal parameters p and γ through the adaptive particle swarm optimization algorithm;

[0087] For each grid cell: Pgrid=∑ i=1 n Wi·Pi; where Pi is the observed value of the i-th rainfall station, and n is the number of rainfall stations affecting the grid;

[0088] Step S13c: Use a mixed weight function to perform weighted averaging on each grid to obtain the corresponding rainfall.

[0089] In this embodiment, the similarity of multi-dimensional terrain features is integrated into the surface rainfall calculation, breaking through the limitation of traditional methods that rely only on distance factors; an adaptive optimization algorithm is used to dynamically determine the model parameters to improve the calculation accuracy and adaptability; the calculation accuracy in sparsely populated areas and surface rainfall is greatly improved compared with traditional methods, and it is particularly suitable for areas with complex terrain.

[0090] Step S14: Collect historical data of agricultural and pastoral areas to calculate historical potential evapotranspiration values ​​of agricultural and pastoral areas, and train a pre-built long-short-term memory model together with the historical actual evapotranspiration values ​​of agricultural and pastoral areas. Extract the agricultural and pastoral area data as input to the trained long-short-term memory model to calculate the actual evapotranspiration values ​​of agricultural and pastoral areas.

[0091] In one embodiment, the step S14 is specifically as follows:

[0092] Step S14a, constructing a long short-term memory model;

[0093] Step S14b: collecting historical data and historical actual evapotranspiration values ​​of agricultural and pastoral areas, and calculating historical potential evapotranspiration values ​​of agricultural and pastoral areas based on the historical data of agricultural and pastoral areas;

[0094] Step S14c: using the historical potential evapotranspiration values ​​and the historical actual evapotranspiration values ​​of the agricultural and pastoral areas as training sets, training the long-short-term memory model and optimizing the model parameters;

[0095] Step S14d: extract the agricultural and pastoral area data and input it into the trained long-short-term memory model to calculate the actual evapotranspiration value of the agricultural and pastoral area.

[0096] In this embodiment, by constructing a multi-input feature space, combining the LSTM time series model with the physical constraint loss function, the evaporation paradox phenomenon is learned and represented, and the fitting accuracy of the relationship between potential evaporation and actual evaporation is improved;

[0097] First, meteorological data, soil moisture data, vegetation index and measured evapotranspiration data are integrated to calculate potential evapotranspiration, and characteristic indicators related to radiation trend, wind speed trend, vapor pressure deficit and evaporation paradox are extracted, while daily and seasonal time characteristics are encoded. Then, a long-short-term memory network model is built. Aiming at the contradictory characteristics of potential evapotranspiration and actual evaporation trend in the evaporation paradox, a loss function with dual constraints is designed: on the one hand, the mean square error is used to ensure the fit between the predicted value and the measured value; on the other hand, a paradox penalty term is constructed. When radiation increases but actual evapotranspiration decreases, or radiation decreases but actual evapotranspiration increases, the model prediction error is weighted and amplified by superposition. Parameter adjustment achieves balanced optimization of the two constraints. During the model training phase, the dataset is divided into training and test sets in an 8:2 ratio. An early stopping mechanism is used to prevent overfitting, and time series samples are constructed through a rolling time window for model training. Finally, based on the trained model, preprocessed multi-source data are input, and actual evapotranspiration data are output hourly or daily. This method transforms the evaporation paradox phenomenon into computable constraints through in-depth mining of data features and innovative design of model structure. Compared with traditional empirical models, the improved accuracy of actual evaporation prediction in areas with significant evaporation paradox effectively solves the problem of insufficient explanatory power of traditional methods for complex hydrological phenomena.

[0098] In this embodiment, a special constraint loss function is designed for the evaporation paradox phenomenon to solve the technical problem that the traditional model cannot effectively deal with the contradiction between potential evaporation and actual evaporation trends. Specifically, a composite loss function including a paradox penalty term is constructed: L total =L mse +λ×L paradox ;

[0099] Among them, L mse is the mean square error loss function, λ is the paradox penalty weight coefficient, L paradox is the paradox penalty term.

[0100] The specific calculation method of the paradox penalty term Lparadox is:

[0101] Lparadox=Σ[wi×max(0,sign(ΔRi)×sign(ΔETactual_i)+1)];

[0102] Among them, w i is the weight of the i-th time step, ΔR i is the radiation change, ΔET actual_i is the actual evapotranspiration change, sign() is the sign function, when radiation increases but actual evapotranspiration decreases, sign(ΔR i )×sign(ΔET actual_i )=-1, making the penalty term 2×w i; When the changing trends of the two are consistent, the penalty term is 0.

[0103] It should be noted that the value range of the weight coefficient λ is 0.1-0.5, preferably 0.3, and the weight w_i is determined according to the intensity of the evaporation paradox phenomenon, and the calculation formula is: w i =|ΔR i | / (|ΔR i |+|ΔET potential_i| );

[0104] Through the above-mentioned paradox penalty mechanism, the model focuses on correcting prediction results that violate physical laws during training, thereby improving the prediction accuracy in areas where the evaporation paradox is significant.

[0105] In some embodiments, a segment penalty strategy is optionally adopted. When |ΔR i When the value is greater than the preset threshold, the penalty weight is doubled, further strengthening the constraint effect on the strong evaporation paradox phenomenon.

[0106] For example, in a test in a drought-stricken area, when daily radiation increased by 15% and actual evapotranspiration decreased by 8%, the paradox penalty term was 0.46, significantly improving the model's ability to identify and correct such abnormal situations.

[0107] Step S15: Calculate the historical available water volume in the agricultural and pastoral areas based on the historical rainfall and historical potential evapotranspiration values ​​in the agricultural and pastoral areas, perform soil and water balance calculations on the agricultural and pastoral areas based on the agricultural and pastoral area data, obtain the historical water demand in the agricultural and pastoral areas, calculate the historical water demand of each grid in the agricultural and pastoral areas, extract several drought centers, and divide the agricultural and pastoral areas into several sub-areas.

[0108] The soil and water balance calculation method that integrates the evaporation paradox provided by the present invention creatively combines machine learning technologies such as geographically weighted regression and long short-term memory networks with traditional hydrological calculation models, and improves the shortcomings of traditional methods in rainfall calculation, evapotranspiration processing and soil and water balance assessment. By introducing the evaporation paradox as a constraint condition to optimize the evaporation calculation model, and combining land standards and crop characteristics in agricultural and pastoral areas, it realizes the precise integrated calculation of rainfall, evapotranspiration and soil and water balance driven by multi-source data, which has significantly improved the calculation accuracy and practicality compared with existing technologies.

[0109] According to one aspect of the present application, step S12 is further as follows:

[0110] Step S12a, extracting the agricultural and pastoral area terrain data, setting the grid resolution to grid the agricultural and pastoral area, and obtaining the agricultural and pastoral area terrain grid;

[0111] Step S12b: Based on the grid resolution of the agricultural and pastoral terrain, the rainfall station data is converted into a spatial distribution grid using the inverse distance weighted method;

[0112] Step S12c: Integrate the agricultural and pastoral area terrain grid and the rainfall spatial distribution grid to obtain the agricultural and pastoral area terrain feature matrix.

[0113] In a certain embodiment, specifically:

[0114] Extract the terrain data of agricultural and pastoral area A from the geographic information system database, including contour lines and elevation point information. Set the grid resolution to 100 meters × 100 meters, grid the agricultural and pastoral area, and obtain 50,000 terrain grids, each of which contains corresponding terrain information.

[0115] There are 10 rain gauges distributed throughout the agricultural and pastoral area, recording rainfall data for the past year. Based on a set grid resolution of 100 meters, the observed data from these 10 rain gauges were converted into a spatial distribution grid using the inverse distance weighted method (IDW). This method estimates rainfall for each grid by assigning different weights based on the distance between the rain gauge and the point to be interpolated. The closer the distance, the greater the weight.

[0116] The agricultural and pastoral area terrain grid obtained in step S12a and the rainfall spatial distribution grid obtained in step S12b are integrated to obtain an agricultural and pastoral area terrain feature matrix.

[0117] In particular, for the selected inverse distance weighted method, the Kriging interpolation method can also be selected. First, the variation function of the rainfall data is calculated, its spatial variation characteristics are analyzed, and the appropriate semi-variogram model and parameters are determined, such as nugget value, range, and sill value. Then, based on these parameters and the set grid resolution, the rainfall station data is interpolated into a spatial distribution grid, which can obtain a rainfall spatial distribution that is more in line with spatial correlation.

[0118] According to one aspect of the present application, step S15 is further as follows:

[0119] Step S15a, extracting historical rainfall and historical potential evapotranspiration values ​​in the agricultural and pastoral areas, and calculating the historical available water volume in the pastoral areas;

[0120] Step S15b: extract the crop type, irrigation method, soil characteristics, crop water requirement coefficient and crop growth cycle in the agricultural and pastoral areas, calculate the crop water requirement at each time point in each grid in the agricultural and pastoral areas, summarize the living and ecological water requirements, and obtain the historical water requirements of the agricultural and pastoral areas;

[0121] Step S15c: Extract water demand data for each grid at each time point in the agricultural and pastoral areas, map water demand to color and draw a drought distribution map using the grid as a unit, with the color corresponding to the water demand from light to dark from small to large. Superimpose the distribution maps at each time point, calculate the total and average water demand of each grid, extract grids whose total and average water demand are both greater than a threshold, and divide the connected grids into the same area to obtain several drought centers;

[0122] Preferably, the following can also be done: extract water demand data for each grid at each time point in the agricultural and pastoral areas, map the water demand to colors using the grid as a unit to draw a drought distribution map, with the water demand corresponding to colors from light to dark from small to large, superimpose the distribution maps at each time point to calculate the total water demand and average value of each grid, use an adaptive threshold determination method based on statistical analysis to calculate the threshold, extract grids whose total water demand and average value are both greater than the threshold, and use a dual connectivity judgment standard based on spatial adjacency and water demand similarity to divide the connected grids into the same area to obtain several drought centers.

[0123] Furthermore, the mean and standard deviation of water demand for all grids were calculated, and the skewness and kurtosis of water demand in the study area were calculated. The adjustment coefficient was determined according to the distribution morphology. When the absolute value of the skewness was less than or equal to 0.5 and the absolute value of the difference between the kurtosis and 3 was less than or equal to 0.5, the adjustment coefficient was 1.5. When the skewness was greater than 0.5, the adjustment coefficient was 1.2. When the skewness was less than -0.5, the adjustment coefficient was 1.8. The adjustment coefficient was adjusted according to the kurtosis, and the final threshold was obtained by sliding window smoothing.

[0124] Furthermore, the two grids are judged to be adjacent within the 8-neighborhood range and the distance between the grid center points is less than or equal to the square root of 2 times the grid side length. The relative error of the water demand difference between the two grids is calculated. When the relative error is less than the similarity threshold, it is determined to be connected. The similarity threshold is determined according to the coefficient of variation of the water demand of all adjacent grid pairs in the study area. The depth-first search method is used to identify the connected area, and the minimum area constraint is set to avoid the formation of too small a drought center.

[0125] Step S15d: Based on the spatial distribution of drought centers, the agricultural and pastoral areas are divided into several sub-areas using Thiessen polygons, each of which contains a drought center.

[0126] In a certain embodiment, specifically:

[0127] The area of ​​agricultural and pastoral area A is 500 square kilometers. If the grid resolution is set to 100 meters × 100 meters, there will be 50,000 grids in total.

[0128] The researchers extracted historical rainfall data and potential evapotranspiration values ​​for the past 10 years from the local meteorological department and water resources monitoring database. For example, in January 2014, the average rainfall in the area was 10 mm, and the average potential evapotranspiration was 15 mm; in February 2014, the average rainfall was 8 mm, and the average potential evapotranspiration was 12 mm, resulting in 120 months of relevant data.

[0129] Convert the rainfall and potential evapotranspiration data into raster data. Use the raster calculator to calculate the available water volume for each pixel each month, where available water volume = rainfall minus potential evapotranspiration. For example, in January 2014, if the rainfall in a grid was 12 mm and the potential evapotranspiration was 16 mm, the available water volume for that grid would be -4 mm. This yields a raster dataset of the available water volume for the past 10 years in agricultural and pastoral area A.

[0130] Extract crop types, irrigation methods, soil characteristics, crop water requirement coefficients and crop growth cycles in agricultural and pastoral areas, specifically:

[0131] Wheat planting area accounts for 30%, 15,000 grids; corn planting area accounts for 25%, 12,500 grids; forage planting area accounts for 45%, 22,500 grids;

[0132] Drip irrigation covers 60% of farmland, 30,000 grids; sprinkler irrigation covers 30%, 15,000 grids; flood irrigation covers 10%, 5,000 grids;

[0133] The sandy soil area accounts for 20%, with 10,000 grids; the loamy soil area accounts for 50%, with 25,000 grids; and the clay soil area accounts for 30%, with 15,000 grids.

[0134] The water requirement coefficient of wheat in the early growth period is 0.3, 0.6 in the middle growth period, and 0.4 in the late growth period; the water requirement coefficient of corn in the early growth period is 0.2, 0.7 in the middle growth period, and 0.3 in the late growth period; the average water requirement coefficient of forage grass during the growing season is 0.5;

[0135] The wheat growing cycle is 5 months, the corn growing cycle is 4 months, and pasture grows all year round.

[0136] For each grid, the crop water requirement at each time point is calculated based on its crop type, growth cycle, water requirement coefficient, and irrigation method, combined with meteorological data;

[0137] For example, in a loam grid where wheat is grown, the rainfall in the middle growth period is 20 mm, and the potential evapotranspiration is 30 mm. Based on local meteorological data and the crop water requirement coefficient, the crop water requirement for this grid is (30-20)×0.6=6 mm.

[0138] The population of this agricultural and pastoral area is about 10,000, and the monthly per capita domestic water quota is 3m 3 , converting it to each grid, the living water demand of each grid is about 10000×3÷50000=0.6m 3 , converted to a depth of approximately 0.6×1000÷(100×100)=0.06mm;

[0139] The ecological water demand quota for this agricultural and pastoral area is 0.5 mm per month. The total water demand at each time point of each grid is summarized to obtain the historical water demand data of the agricultural and pastoral area.

[0140] Extract the water demand data for each grid at each time point, use the grid as a unit, map the water demand to the color and draw a drought distribution map. Set the color from light blue to dark blue as the water demand increases. Superimpose the drought distribution map for each month, and calculate the total and average water demand of each grid over 10 years.

[0141] The average water demand of all grids over 10 years is 500 mm. The threshold is set to 1.5 times the average value, that is, 750 mm. The grids whose total water demand and average value are both greater than the threshold are extracted. The total water demand over 10 years is 800 mm and the average value is 80 mm. The connected grids are divided into the same area, thereby determining several drought centers.

[0142] In step S15c of this embodiment, the threshold is determined using an adaptive method based on statistical analysis to solve the technical problem that a fixed threshold cannot adapt to the differences in hydrological characteristics of different regions. Specifically, the threshold T = μ + k × σ; where μ is the mean of the water demand of all grids, σ is the standard deviation, and k is the adjustment coefficient.

[0143] The method for determining the adjustment coefficient k includes the following steps:

[0144] First, the distribution characteristic parameters of water demand in the study area are calculated, including skewness S and kurtosis K;

[0145] Then, the k value is determined according to the distribution shape: when |S|≤0.5 and |K-3|≤0.5, the data is close to normal distribution, and the k value is 1.5; when S>0.5, the data is right-skewed, and the k value is 1.2; when S<-0.5, the data is left-skewed, and the k value is 1.8; when |K-3|>0.5, the k value is adjusted according to the kurtosis, and k is increased by 0.2 when the kurtosis is high, and k is reduced by 0.2 when the kurtosis is low.

[0146] It should be noted that in order to improve the stability of the threshold, a sliding window smoothing process is used:

[0147] T final =0.4×T current +0.3×T previous +0.3×T next ;

[0148] Where T current is the currently calculated threshold, T previous and T next are the thresholds for adjacent time periods respectively.

[0149] In some embodiments, the quantile method is optionally used to determine the threshold value. The 75th percentile is taken as the benchmark threshold value, and for extremely arid regions, it can be adjusted to the 85th percentile.

[0150] For example, in a 500-square-kilometer research area, the average water demand of the grid is 45 mm, the standard deviation is 12 mm, and the skewness is 0.3. Then the value of k is 1.5, and the calculated threshold value T = 45 + 1.5×12 = 63 mm. After smoothing by a sliding window, the final threshold value is 61.5 mm.

[0151] In step S15c, the connected grids are divided into the same area to obtain several drought centers. The implementation process is as follows:

[0152] In this embodiment, the connectivity judgment adopts a dual standard based on spatial adjacency relationship and water demand similarity to solve the unreasonable clustering problem that may be caused by simple spatial adjacency. Specifically, two grids are judged to be connected if they simultaneously meet the following conditions:

[0153] Spatial adjacency condition: The two grids are adjacent within the 8-neighborhood range, that is, the distance d between the grid center points ≤ sqrt(2)×grid_size, where grid_size is the side length of the grid;

[0154] Water demand similarity condition: The relative error of the difference in water demand between the two grids is less than the threshold value. The calculation formula is:

[0155] |W i -W j | / max(W i ,W j )≤ε;

[0156] Among them, W i and W j are the water demands of the two grids respectively, and ε is the similarity threshold value.

[0157] The method for determining the similarity threshold value ε is: <00​​​​​​​​​​​

[0161] It should be noted that in order to avoid the formation of too small a drought center, a minimum area constraint is set;

[0162] The number of grids contained in the connected area is not less than: N min =max(9,0.01×N total ), where N total is the total number of grids in the study area. Small areas that do not meet the area constraint will be merged into the adjacent largest connected area.

[0163] In some embodiments, a correction method based on terrain connectivity is optionally adopted. When two high-water-demand grids are separated by a terrain barrier (such as a ridge or a river), they are not determined to be connected even if the spatial and similarity conditions are met.

[0164] For example, in the study area with a grid resolution of 100m×100m, the water demands of two adjacent grids are 68mm and 72mm respectively, with a relative error of 5.9%, which is less than the threshold of 15%, and the spatial distance is 100m, which meets the connection conditions and is divided into the same drought center area.

[0165] The above dual judgment criteria ensure the accuracy and rationality of drought center identification, and avoid the problem of incorrect clustering of spatially adjacent grids with significant differences in hydrological characteristics.

[0166] According to one aspect of the present application, step S15 may also be:

[0167] Construct a time inversion prediction model to calculate the hydrological state constraints in the future period and obtain the historical available water volume in the agricultural and pastoral areas through backpropagation;

[0168] Combined with the time reversal constraint factor, the predictive crop water demand of each grid at each time point in the agricultural and pastoral areas is calculated, and the future water demand change trend of the living ecology is summarized to obtain the predictive water demand of the agricultural and pastoral areas integrated with the time reversal weight.

[0169] Based on the time inversion constraint, the dynamic foresight threshold is calculated, the foresighted water demand risk is mapped to color to draw the drought risk distribution map, the foresighted drought intensity of each grid is calculated, and the grids with foresighted drought intensity greater than the dynamic threshold are extracted;

[0170] The back propagation connectivity algorithm is used to divide the agricultural and pastoral areas into several predictive drought-affected sub-regions, each of which contains a predictive drought center.

[0171] Furthermore, the back propagation connectivity algorithm includes:

[0172] Calculate the back-propagation gradient, set spatial gradient constraints, time synchronization constraints and influence intensity constraints, identify the back-propagation seed points, build the propagation tree structure with the seed points as the root nodes according to the reverse gradient direction, determine the clustering boundaries based on the attenuation characteristics of the time inversion intensity, adopt a competitive allocation mechanism to avoid cluster overlap, and use multi-time scale clustering verification to ensure the stability of the clustering results.

[0173] Furthermore, the calculation of predictive water demand in agricultural and pastoral areas integrating time inversion weights includes:

[0174] The predictive water demand is calculated by multiplying the basic water demand by the future constraint correction coefficient and the time reversal correction factor. The future constraint correction coefficient is determined by the water demand trend factor, and the time reversal correction factor is calculated based on the time reversal operator. The domestic water demand takes into account population growth and changes in water use habits, and the ecological water demand incorporates the ecosystem's response mechanism to drought. The multi-scenario weighted average method is used to improve the accuracy of the predictive water demand.

[0175] Specifically, the steps include:

[0176] Step S151: extract historical rainfall and historical potential evapotranspiration values ​​in agricultural and pastoral areas, construct a time inversion prediction model, calculate the hydrological state constraints of future periods, and obtain the back-propagated historical available water volume in the pastoral areas;

[0177] In this embodiment, time reversal prediction adopts a hydrological state deduction method based on causal inversion to solve the technical problem that traditional historical statistics cannot predict future drought development trends. Specifically, a time reversal operator T_rev is constructed:

[0178] Ψ(x,y,t) = ∫[t to t+ΔT] K_rev(τ-t) × S_future(x,y,τ) × w(τ) dτ;

[0179] Among them, K_rev(τ-t) is the time inversion kernel function, S_future(x,y,τ) is the estimated hydrological state at the future time τ, w(τ) is the time weight function, and ΔT is the foresight time window.

[0180] Time reversal kernel function: K_rev(τ-t) = exp(-α×(τ-t)²) × cos(β×(τ-t));

[0181] Wherein, α is the attenuation coefficient, ranging from 0.01 to 0.05, preferably 0.03; β is the oscillation frequency parameter, ranging from 0.1 to 0.5, preferably 0.25.

[0182] It should be noted that the future hydrological state S_future is obtained through the improved long short-term memory network prediction. The prediction time window is set to 30-90 days, preferably 60 days, and the time weight function w(τ) adopts the exponential decay form:

[0183] w(τ) = exp(-γ×(τ-t) / ΔT)

[0184] Here, γ is a weight attenuation factor, which ranges from 1.5 to 2.5, preferably 2.0.

[0185] For example, when calculating the hydrological status of a grid in April, considering the projected decreasing trend in rainfall and increasing trend in temperature over the next 60 days, the time reversal operator Ψ = 0.75, indicating that the location has a high risk of future drought.

[0186] Step S152: Extract the crop type, irrigation method, soil characteristics, crop water requirement coefficient, and crop growth cycle in the agricultural and pastoral areas, and calculate the predicted crop water requirement at each time point for each grid in the agricultural and pastoral areas in combination with the time inversion constraint factor. Summarize the future water demand trends for life and ecology to obtain the predicted water demand for the agricultural and pastoral areas integrated with the time inversion weight.

[0187] In this embodiment, the predictive water demand calculation adopts a dynamic weight allocation method based on future constraints to solve the technical problem that the traditional water demand calculation only considers the current state and cannot reflect future changes in water demand pressure.

[0188] Specifically, predictive water demand W_predictive(x,y,t) = W_base(x,y,t) × [1 + λ_future × F_trend(x,y,t)] × R_rev(x,y,t);

[0189] Among them, W_base(x,y,t) is the basic water demand, λ_future is the future constraint weight coefficient, F_trend(x,y,t) is the water demand trend factor, and R_rev(x,y,t) is the time reversal correction factor.

[0190] Basic water requirement W_base(x,y,t) = ET0(t) × K_c(crop,stage) × K_s(soil) ×A_effective(x,y);

[0191] Among them, ET0 is the reference evapotranspiration, K_c is the crop coefficient, K_s is the soil coefficient, and A_effective is the effective irrigation area.

[0192] Water demand trend factor F_trend(x,y,t) = Σ[i=1 to n] w_stage_i × K_c_future(t+i×Δt) / K_c_current(t);

[0193] Among them, w_stage_i is the weight of the future i-th growth stage, K_c_future is the predicted future crop coefficient, and n is the number of foreseen stages, usually 3-5 stages.

[0194] The time reversal correction factor R_rev is calculated based on the time reversal operator in step S151:

[0195] R_rev(x,y,t) = 1 + β_rev × [Ψ(x,y,t) - Ψ_mean] / Ψ_std;

[0196] Where β_rev is the inversion correction coefficient, ranging from 0.1 to 0.4, with a preferred value of 0.25; Ψ_mean and Ψ_std are the mean and standard deviation of the regional time inversion operator, respectively.

[0197] The future constraint weight coefficient λ_future is dynamically adjusted according to the prediction confidence and time distance:

[0198] λ_future = λ_max × confidence_score × exp(-decay_rate × t_distance);

[0199] Among them, λ_max is the maximum weight coefficient, ranging from 0.3 to 0.7, preferably 0.5; confidence_score is the prediction confidence; decay_rate is the time decay rate, ranging from 0.02 to 0.05; t_distance is the time distance.

[0200] Foresight calculations of domestic water demand take into account population growth and changes in water use habits:

[0201] W_domestic_predictive = W_domestic_base × [1 + r_population × t_future + δ_habit × Ψ(x,y,t)];

[0202] Among them, r_population is the population growth rate, and δ_habit is the coefficient of change of water use habits.

[0203] Predictive calculation of ecological water demand is integrated into the ecosystem's response mechanism to drought:

[0204] W_ecological_predictive = W_ecological_base × [1 + ε_stress × max(0, Ψ(x,y,t) - Ψ_threshold)];

[0205] Among them, ε_stress is the ecological stress coefficient, and Ψ_threshold is the ecological stress threshold.

[0206] It should be noted that in order to improve the accuracy of predictive water demand, a multi-scenario weighted average method is adopted:

[0207] W_final = Σ[k=1 to m] p_scenario_k × W_predictive_k;

[0208] Where m is the number of scenarios, which is usually set to 3 (optimistic, baseline, and pessimistic), and p_scenario_k is the probability weight of the kth scenario.

[0209] In some embodiments, a rolling update mechanism is optionally adopted to update the time inversion weights and predictive water demand every 7-15 days based on the latest observation data and forecast results.

[0210] For example, the baseline water requirement for a wheat planting grid in mid-April is 8.5 mm / week. Considering the increasing trend in water demand during the future peak growth period, F_trend = 1.35. The time reversal operator Ψ for this grid is 1.2, which is 0.8 higher than the regional average, R_rev = 1.1. The final predictive water requirement is 8.5 × [1 + 0.5 × 1.35] × 1.1 = 14.6 mm / week, a 72% increase over the baseline water requirement.

[0211] Step S153: Extract water demand data for each grid in the agricultural and pastoral areas at each time point, calculate a dynamic foresight threshold based on time inversion constraints, map the foresighted water demand risk to color, and draw a drought risk distribution map. The colors are from light to dark corresponding to the risk from small to large. The time inversion weight is superimposed, and the foresighted drought intensity of each grid is calculated. Grids with foresighted drought intensity greater than the dynamic threshold are extracted, and the grids that meet the reverse connectivity condition are divided into the same area to obtain a number of foresighted drought centers.

[0212] In this embodiment, the dynamic threshold T_dynamic adopts an adaptive calculation method with time inversion constraints to solve the technical problem that the traditional static threshold cannot reflect the dynamic evolution trend of drought.

[0213] Specifically, the calculation formula of the dynamic threshold is:

[0214] T_dynamic(x,y,t) = T_base × [1 + λ_rev × Ψ(x,y,t)] × F_trend(t);

[0215] Wherein, T_base is the base threshold, λ_rev is the time reversal weight coefficient, Ψ(x, y, t) is the time reversal operator value calculated in step S15a, and F_trend(t) is the trend correction factor.

[0216] Base threshold: T_base = Q 75 + k_adaptive × IQR;

[0217] Among them, Q 75 is the 75th percentile of water demand, IQR is the interquartile range, and k_adaptive is the adaptive adjustment coefficient.

[0218] The adaptive adjustment coefficient k_adaptive is determined according to the regional hydrological variability:

[0219] k_adaptive = 0.5 × [1 + tanh(CV_hydro - 0.3)];

[0220] Where CV_hydro is the regional hydrological variation coefficient. When CV_hydro ≤ 0.3, k_adaptive ≈ 0.5; when CV_hydro ≥ 0.6, k_adaptive ≈ 1.0.

[0221] The time reversal weight coefficient λ_rev ranges from 0.2 to 0.8 and is dynamically adjusted according to the prediction confidence:

[0222] λ_rev = 0.2 + 0.6 × confidence_score;

[0223] Among them, confidence_score is the confidence score of the future state prediction, ranging from 0 to 1.

[0224] The trend correction factor F_trend(t) takes into account seasonal and interannual variations:

[0225] F_trend(t) = 1 + A_seasonal × sin(2π×t / 365) + A_interannual × sin(2π×t / 1095);

[0226] Among them, A_seasonal is the seasonal amplitude coefficient, which ranges from 0.1 to 0.3; A_interannual is the interannual amplitude coefficient, which ranges from 0.05 to 0.15.

[0227] It should be noted that the calculation of the predictive drought intensity I_predictive integrates the current state and future constraints:

[0228] I_predictive(x,y,t) = α_current × W_current(x,y,t) + α_future × Ψ(x,y,t);

[0229] Among them, α_current and α_future are the weight coefficients of the current and future states, satisfying α_current + α_future = 1, and preferably α_current = 0.4 and α_future = 0.6.

[0230] In some embodiments, a multi-level threshold strategy may be optionally adopted to set warning thresholds, severe thresholds, and extreme thresholds, which correspond to different levels of predictive drought centers, respectively.

[0231] For example, in the calculation in May in a certain agricultural and pastoral area, the base threshold T_base = 52 mm, the time reversal operator Ψ = 1.2, λ_rev = 0.5, and F_trend = 1.1, then the dynamic threshold T_dynamic = 52 × [1 + 0.5 × 1.2] × 1.1 = 86.3 mm.

[0232] Step S154: Based on the spatiotemporal distribution characteristics of the predictive drought centers, the back propagation connectivity algorithm is used to divide the agricultural and pastoral areas into several predictive drought-affected sub-regions, each of which contains a dominant predictive drought center.

[0233] In this embodiment, the reverse connectivity judgment adopts a propagation path identification method based on the time inversion gradient field to solve the technical problem that traditional spatial adjacency cannot reflect the dynamic expansion of the drought impact range. Specifically, the calculation formula of the reverse propagation gradient G_backward is:

[0234] G_backward(x,y,t) = -grad [Ψ(x,y,t+Δt) - Ψ(x,y,t)];

[0235] Where grad is the gradient operator and Δt is the time step, which ranges from 1 to 7 days, with 3 days being the preferred value.

[0236] The reverse connectivity condition includes the following three constraints:

[0237] Spatial gradient constraint: The reverse gradient direction consistency between two grids satisfies:

[0238] cos(θ_gradient) = G_i · G_j / (|G_i| × |G_j|) ≥ θ_threshold;

[0239] Here, θ_threshold is an angle threshold, ranging from cos(45°) to cos(30°), preferably cos(35°)≈0.819.

[0240] Time synchronization constraint: The time phase difference of drought development between the two grids is less than the allowable range:

[0241] |Phase_i(t) - Phase_j(t)| ≤ Δφ_max; where Phase is the temporal phase of drought development and Δφ_max is the maximum phase difference, ranging from π / 6 to π / 4, with π / 5 being the preferred value.

[0242] Impact intensity constraint: The relative difference in predictive drought intensity of connected grids satisfies the following condition: |I_predictive_i -I_predictive_j| / max(I_predictive_i, I_predictive_j) ≤ ε_intensity; where ε_intensity is the intensity similarity threshold, ranging from 0.15 to 0.35, with 0.25 being the preferred value.

[0243] The predictive clustering algorithm uses an improved back-propagation clustering method:

[0244] Step 1. Identify the backpropagation seed point: Starting from the grid with the highest predicted drought intensity, calculate its backpropagation influence domain: Seed_influence(x0,y0) = {(x,y) | G_backward(x,y) → (x0,y0)};

[0245] Step 2: Construct a back propagation tree: Take the seed point as the root node and construct the propagation tree structure in the reverse gradient direction:

[0246] Tree_node(x,y) = {parent: (x0,y0), children: {(xi,yi)}, weight: I_predictive(x,y)};

[0247] Step 3: Dynamic boundary determination: Determine the cluster boundary based on the attenuation characteristics of the time inversion intensity.

[0248] Boundary_condition: I_predictive(x,y) ≥ I_seed × exp(-β_decay × d_propagation);

[0249] Among them, I_seed is the predicted drought intensity of the seed point, β_decay is the decay coefficient, which ranges from 0.1 to 0.3, and d_propagation is the propagation distance.

[0250] It should be noted that in order to avoid cluster overlap, a competitive allocation mechanism is adopted: when a grid meets the connectivity conditions of multiple clusters at the same time, it is allocated to the cluster center with the largest backpropagation intensity.

[0251] In some embodiments, multi-time-scale clustering verification is optionally used to ensure the stability of clustering results in different time windows. The verification method is: Stability_score = Σ[Overlap(Cluster_t, Cluster_t+Δt)] / |Cluster_t|; when the stability score is lower than 0.7, the clustering parameters are adjusted and recalculated.

[0252] For example, in a certain 500 square kilometer study area, three predictive drought centers were identified, of which the backpropagation influence domain of the main center covered 180 square kilometers, and the secondary centers covered 120 and 80 square kilometers respectively. The time phase differences among the three centers were 5 days, 8 days, and 12 days, respectively, which met the spatiotemporal evolution laws of predictive drought development.

[0253] Through the above-mentioned time-reversal predictive drought center identification method, a technological leap from traditional historical statistical identification to future constrained foresight has been achieved, which has improved the foresight and accuracy of drought center identification and provided a scientific basis for the advanced allocation of water resources in agricultural and pastoral areas.

[0254] like Figure 3 As shown, according to one aspect of the present application, step S2 is further:

[0255] Step S21: Collecting hydrological station detection data and using cross-sectional flow calculation method to collect water flow data at different frequencies;

[0256] Water inflow data is the basis for water source planning in irrigation areas. Water inflow at different frequencies can reflect the stability of water supply and changes in water supply. A suitable section is selected at the hydrological station, and the flow velocity at different positions of the section is measured using a flow meter. The average flow velocity is calculated. At the same time, the area of ​​the section is measured and the flow rate is calculated. Repeat the measurement multiple times to take the average value to obtain water inflow data at different frequencies.

[0257] Step S22: collecting hydrological data and water level dynamic changes, detecting water quality parameters, water quality indicators and water quantity parameters, and drawing a water layer distribution map;

[0258] Step S23: Calculate the water quality rate based on the water source water quantity data and the water demand, determine the feasibility of water extraction based on the elevation difference between the water source water level and the water intake point in the irrigation area, and select the water intake;

[0259] Step S24: construct surface water source engineering plans and groundwater source engineering plans based on the spatial distribution of drought centers, and combine them to obtain water source engineering layout plans for each sub-region.

[0260] According to one aspect of the present application, step S24 is further as follows:

[0261] Step S24a: Collect groundwater level monitoring data and river and lake water level data for each sub-region, draw a water level contour map based on water demand, extract the coordinates of the water level contour lines, and calculate the slope of each contour line;

[0262] Step S24b: Set an initial buffer distance, generate a circular initial buffer zone with the drought center as the center, modify the initial buffer zone based on the density of water level contour lines, set a slope threshold, and divide the buffer zone into a core buffer zone and a secondary buffer zone based on the calculated contour line slopes;

[0263] Step S24c: construct surface water source engineering schemes and groundwater source engineering schemes for each sub-region for the core buffer zone and the secondary buffer zone, input the pre-constructed water resources joint scheduling model, and solve the model to obtain the water source engineering layout scheme for each sub-region.

[0264] In a certain embodiment, specifically:

[0265] Agricultural and pastoral area B covers an area of ​​approximately 500 square kilometers and is divided into five sub-areas based on the identified drought center. Groundwater level monitoring data for each sub-area over the past three years was collected through the water conservancy department's monitoring network. In sub-area 1, the groundwater level at monitoring point M was 15 meters on January 1, 2021, and the groundwater level at monitoring point N was 16 meters. River and lake water level data were also collected. A river in sub-area 2 had a water level of 8 meters on January 1, 2021, and a water level of 7.8 meters on February 1, 2021. Combined with the water demand data for each sub-area calculated previously, the annual water demand for the sub-area is 8 million cubic meters, and the annual water demand for the sub-area is 6 million cubic meters.

[0266] Interpolate the groundwater level data and river and lake water level data to generate groundwater level raster data and river and lake water level raster data, and draw groundwater level contour maps and river and lake water level contour maps respectively;

[0267] Calculate the slope of each contour line based on the coordinate data. For example, for a contour line, select two adjacent points (x1, y1) and (x2, y2), and the slope k = (y2-y1) ÷ (x2-x1). For example, if the coordinates of two adjacent points on a groundwater level contour line are (100, 15) and (200, 14), its slope k = (14-15) ÷ (200-100) = -0.01.

[0268] The initial buffer distance is set to 500 meters, and a circular initial buffer zone is generated with each drought center as the center;

[0269] The slope threshold is set to 0.02. Based on the calculated water level contour slope, the initial buffer zone is modified. If the absolute value of the contour slope is greater than the threshold, it means that the water level changes dramatically. If it is less than the threshold, the water level changes relatively slowly. The buffer zone is divided into a core buffer zone and a secondary buffer zone. The area with the absolute value of the contour slope greater than the threshold is divided into a core buffer zone, and the area with the absolute value of the contour slope less than the threshold is divided into a secondary buffer zone.

[0270] For the core buffer zone, considering the large fluctuations in water resources, the surface water source project plan will include the construction of reservoirs or ponds with strong regulation capabilities; the groundwater source project plan will include the deployment of deep wells; for the secondary buffer zone, the surface water source project plan will use small water diversion channels and pumping station facilities; the groundwater source project plan will include the deployment of shallow wells;

[0271] The constructed surface water and groundwater source engineering plans for each sub-region were input into the pre-built water resources joint scheduling model for solution, and the water source engineering layout plans for each sub-region were obtained. Sub-region 1 was finally determined to build a medium-sized reservoir in the core buffer zone and arrange three deep water wells; five small water diversion channels were built in the secondary buffer zone and 10 shallow water wells were arranged.

[0272] In another embodiment, the step S24 is further:

[0273] Step S24a: Collect groundwater level monitoring data and river and lake water level data for each sub-region, draw a water level contour map based on water demand, extract the coordinates of the water level contour lines, and calculate the slope of each contour line;

[0274] Step S24b: With the drought center as the center, an initial buffer distance is set to generate a circular initial buffer zone. The spatial distribution of water level contours and water demand distribution are used as input parameters. With construction cost, water resource utilization efficiency, and ecological impact as optimization targets, the initial buffer zone is optimized and divided to obtain areas with different functions and priorities. Specifically, areas close to water sources and with low construction costs are divided into priority construction areas, and areas with complex water resource conditions and high construction costs are divided into cautious construction areas.

[0275] Step S24c: construct surface water source engineering schemes and groundwater source engineering schemes respectively according to the optimized divided areas.

[0276] like Figure 4 As shown, according to one aspect of the present application, step S3 is further:

[0277] Step S31: collecting the terrain slope of the irrigation area, the soil permeability coefficient, the distribution of crop planting areas, and the location of the water outlet of the water source project;

[0278] Step S32: Select an irrigation system based on the terrain slope, and calculate the pipe diameter, dripper spacing, channel cross-sectional dimensions, and pump station head;

[0279] For areas with a terrain slope of less than 15°, drip irrigation and pipe irrigation systems are selected. The pipe diameter and dripper spacing are calculated according to relevant formulas based on the irrigation flow and pressure requirements. For areas with a terrain slope greater than 15°, pump stations and open channel irrigation systems are selected. Based on the terrain height difference and flow, hydraulic formulas are used to calculate the channel cross-sectional dimensions and pump station head, thereby determining the irrigation system suitable for different terrain slopes and accurate engineering parameters.

[0280] Step S33: construct drainage projects based on the rainstorm intensity data and topographic water catchment data of each sub-region, and obtain the irrigation project layout plan for each sub-region.

[0281] Collect rainstorm intensity data and topographic water catchment data for each sub-region, apply drainage engineering design principles and calculation formulas to determine the direction, cross-sectional dimensions, and slope parameters of drainage channels, design drainage pumping stations and other facilities, construct drainage projects, and combine them with irrigation projects to form a complete irrigation area project layout plan.

[0282] like Figure 5 As shown, according to one aspect of the present application, step S4 is further:

[0283] Step S41: constructing an evaluation index system, including economic value index, social benefit index and ecological benefit index;

[0284] Based on the characteristics of water network irrigation areas in agricultural and pastoral areas, representative indicators were selected, and the net present value, internal rate of return, and investment payback period were used as economic value indicators, quality of life, employment opportunities, and social stability as social benefit indicators, and the ecological environment quality index as an ecological benefit indicator to construct an evaluation index system.

[0285] Step S42: Calculate the index value of the water network irrigation project layout plan for each sub-region respectively;

[0286] Step S43: construct an economic evaluation model, extract the index values ​​of the water network irrigation project layout plan of each sub-region as the model input, calculate the comprehensive benefit score of the water network irrigation project layout plan of each sub-region, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

[0287] According to one aspect of the present application, step S42 is further as follows:

[0288] Step S42a: Calculate economic benefit indicators using a dynamic analysis method, including net present value, internal rate of return, and payback period;

[0289] Step S42b: Calculate social benefit indicators using the analytic hierarchy process, including: quality of life, employment opportunities, and social stability;

[0290] Step S42c: Calculate the ecological benefit index using the ecological environment quality index method.

[0291] According to one aspect of the present application, step S43 is further as follows:

[0292] Step S43a: Construct a multi-level comprehensive evaluation model, including a target layer, a criterion layer, and an indicator layer. The target layer is the comprehensive benefits of the scale layout plan of the agricultural and pastoral water network irrigation project. The criterion layer includes economic benefits, social benefits, and ecological benefits. The indicator layer is further subdivided according to the criterion layer.

[0293] Step S43b: perform pairwise comparison and scoring of the importance of indicators based on the 1-9 scale method, construct a judgment matrix, calculate the eigenvector and maximum eigenroot of the judgment matrix, perform consistency test, determine the weight of each indicator and configure a multi-level comprehensive evaluation model;

[0294] Step S43c: extract the index values ​​of the water network irrigation project layout plan of each sub-region as the input of the multi-level comprehensive evaluation model, calculate the comprehensive benefit score of the water network irrigation project layout plan of each sub-region, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

[0295] In a certain embodiment, specifically:

[0296] Five experts in water conservancy engineering, economics, sociology, and ecology were invited to compare and score the importance of indicators based on a 1-9 scale. For example, when comparing the importance of economic benefits and social benefits, three experts rated economic benefits as 3, and two experts rated both equally important as 1, resulting in an average of 2.2.

[0297] The judgment matrix is ​​constructed as follows:

[0298] Economic benefits: 1, 2.2, 3;

[0299] Social benefits: 1 / 2.2, 1, 2;

[0300] Ecological benefits: 1 / 3, 1 / 2, 1;

[0301] The eigenvectors and maximum eigenroots of the judgment matrix were calculated, and the weights of economic benefit, social benefit, and ecological benefit were obtained as 0.5, 0.3, and 0.2, respectively;

[0302] Score and calculate each indicator in the indicator layer to obtain specific weights:

[0303] Economic benefit indicator layer: net present value weight 0.4, internal rate of return weight 0.3, investment payback period weight 0.3;

[0304] Social benefit indicator layer: quality of life weight 0.4, employment opportunity weight 0.3, social stability weight 0.3;

[0305] Ecological benefit index layer: vegetation coverage weight 0.2, soil moisture weight 0.2, water quality category weight 0.3, biodiversity index weight 0.3;

[0306] After consistency testing, the consistency ratios of all judgment matrices were less than 0.1, which met the consistency requirements, and the above-mentioned weight configuration multi-level comprehensive evaluation model was determined;

[0307] Substitute the indicator values ​​of each sub-region into the model to calculate the comprehensive benefit score:

[0308] Sub-area 1: Economic benefit score = (net present value score × 0.4 + internal rate of return score × 0.3 + payback period score × 0.3) × 0.5 = ((486.7 / 510) × 10 × 0.4 + 12 / 13 × 10 × 0.3 + (6.5 / 7) × 10 × 0.3) × 0.5 ≈ 4.43;

[0309] Social benefit score = 8.2 × 0.3 = 2.46; ecological benefit score = 4.4 × 0.2 = 0.88; comprehensive benefit score = 4.43 + 2.46 + 0.88 = 7.77;

[0310] Sub-area 2: Economic benefit score = ((320 / 510)×10×0.4+10 / 13×10×0.3+(8 / 7)×10×0.3)×0.5≈3.47;

[0311] Social benefit score = 7.8 × 0.3 = 2.34; ecological benefit score = 3.8 × 0.2 = 0.76; comprehensive benefit score = 3.47 + 2.34 + 0.76 = 6.57;

[0312] Sub-area 3: Economic benefit score = ((510 / 510)×10×0.4+13 / 13×10×0.3+(6.5 / 7)×10×0.3)×0.5≈4.76;

[0313] Social benefit score = 8.5 × 0.3 = 2.55; ecological benefit score = 4.7 × 0.2 = 0.94; comprehensive benefit score = 4.76 + 2.55 + 0.94 = 8.25;

[0314] After comparison, sub-region 3 has the highest comprehensive benefit score, so the water network irrigation area project layout plan of sub-region 3 is determined as the scale layout plan of the water network irrigation area project in the agricultural and pastoral areas.

[0315] By building an economic evaluation model and quantifying the comprehensive benefits of each plan, we can scientifically and objectively select the best plan and achieve optimal resource allocation;

[0316] In this embodiment, the multi-level comprehensive evaluation model can comprehensively consider the influence of multiple levels and multiple indicators. The 1-9 scaling method and judgment matrix calculation can scientifically determine the indicator weights to ensure the rationality and reliability of the evaluation results.

[0317] The present invention fully considers the impact of topography and climate factors on water resources in agricultural and pastoral areas. It first collects agricultural and pastoral data, processes agricultural and pastoral areas through gridding, and constructs a terrain feature matrix. It uses a long-short-term memory model to calculate evapotranspiration values, combines rainfall with soil and water balance calculations, accurately extracts drought centers, and then divides sub-regions.

[0318] Comprehensive consideration of water resource sources, storage, distribution, and discharge ensures that the project layout can adapt to the different water resource conditions and needs of agricultural and pastoral areas. The water inflow of each sub-region is calculated, and the water layer distribution map is drawn. The water intake is determined based on the water quality rate. The water source project is arranged based on the drought center. The irrigation system is determined based on the irrigation area topography. The drainage project is constructed based on the rainstorm intensity and topographic water catchment data to form a complete irrigation area project layout plan.

[0319] Construct an evaluation index system covering many aspects, calculate the index values ​​of the water network irrigation project layout plan for each sub-region, and then use the economic evaluation model to obtain a comprehensive benefit score, and screen the final project scale layout plan through multi-dimensional evaluation.

[0320] According to another aspect of the present application, a system for determining the scale layout of water network irrigation projects in agricultural and pastoral areas is provided, characterized by comprising:

[0321] at least one processor; and

[0322] a memory communicatively connected to at least one of the processors; wherein,

[0323] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement any of the above-mentioned methods for determining the scale layout of water network irrigation projects in agricultural and pastoral areas.

[0324] The preferred embodiments of the present invention are described in detail above. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all fall within the scope of protection of the present invention.

Claims

1. A method for determining the scale and layout of water network irrigation projects in agricultural and pastoral areas, characterized in that: The steps include: Step S1: Collect agricultural and pastoral area data, grid the agricultural and pastoral areas, construct a terrain feature matrix, calculate the rainfall of each grid, use a pre-built long-short-term memory model to calculate the evapotranspiration value, perform soil and water balance calculations, extract several drought centers, and divide the agricultural and pastoral areas into several sub-areas; Step S2: Calculate the water inflow of each sub-region, draw a water layer distribution map, calculate the water quality rate based on the water source water volume data and water demand, determine the water intake, and construct a water source project layout plan for each sub-region based on the spatial distribution of the drought center; Step S3: Extract the water outlet of each sub-region's water source project, combine it with the irrigation area's topographic data, determine the irrigation system, construct a drainage project based on the rainstorm intensity data and topographic water catchment data of each sub-region, and obtain the irrigation project layout plan for each sub-region; Step S4: Construct an evaluation index system, calculate the index values ​​of the water network irrigation project layout plan for each sub-region, input them into the pre-built economic evaluation model, calculate the corresponding comprehensive benefit score, and the highest score is the scale layout plan of the agricultural and pastoral water network irrigation project; The step S1 is further as follows: Step S11, collecting agricultural and pastoral area data, including: agricultural and pastoral area digital elevation data, meteorological data, rainfall station observation data, crop planting structure data, and livestock breeding scale data; Step S12: gridding the study area based on the agricultural and pastoral area terrain data, extracting agricultural and pastoral area digital elevation data and rainfall station observation data, and constructing an agricultural and pastoral area terrain feature matrix; Step S13: Calculate the terrain similarity between each grid and each rainfall station using the Euclidean distance improved by cosine similarity, and optimize the inverse distance weight formula based on the terrain similarity to obtain a hybrid weight function. Use the hybrid weight function to perform weighted averaging on each grid to obtain the corresponding rainfall. Step S14: Collect historical data of agricultural and pastoral areas to calculate historical potential evapotranspiration values ​​of agricultural and pastoral areas, and train a pre-built long-short-term memory model together with the historical actual evapotranspiration values ​​of agricultural and pastoral areas. Extract the agricultural and pastoral area data as input to the trained long-short-term memory model to calculate the actual evapotranspiration values ​​of agricultural and pastoral areas. Step S15: Calculate the historical available water volume in the agricultural and pastoral areas based on the historical rainfall and historical potential evapotranspiration values ​​in the agricultural and pastoral areas, perform soil and water balance calculations on the agricultural and pastoral areas based on the agricultural and pastoral area data, obtain the historical water demand in the agricultural and pastoral areas, calculate the historical water demand of each grid in the agricultural and pastoral areas, extract several drought centers, and divide the agricultural and pastoral areas into several sub-areas.

2. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 1, characterized in that: The step S12 is further as follows: Step S12a, extracting the agricultural and pastoral area terrain data, setting the grid resolution to grid the agricultural and pastoral area, and obtaining the agricultural and pastoral area terrain grid; Step S12b: Based on the grid resolution of the agricultural and pastoral terrain, the rainfall station data is converted into a spatial distribution grid using the inverse distance weighted method; Step S12c: Integrate the agricultural and pastoral area terrain grid and the rainfall spatial distribution grid to obtain the agricultural and pastoral area terrain feature matrix.

3. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 1, characterized in that: The step S15 is further as follows: Step S15a, extracting historical rainfall and historical potential evapotranspiration values ​​in the agricultural and pastoral areas, and calculating the historical available water volume in the pastoral areas; Step S15b: extract the crop type, irrigation method, soil characteristics, crop water requirement coefficient and crop growth cycle in the agricultural and pastoral areas, calculate the crop water requirement at each time point in each grid in the agricultural and pastoral areas, summarize the living and ecological water requirements, and obtain the historical water requirements of the agricultural and pastoral areas; Step S15c: Extract water demand data for each grid at each time point in the agricultural and pastoral areas, map water demand to color and draw a drought distribution map using the grid as a unit, with the color corresponding to the water demand from light to dark from small to large. Superimpose the distribution maps at each time point, calculate the total and average water demand of each grid, extract grids whose total and average water demand are both greater than a threshold, and divide the connected grids into the same area to obtain several drought centers; Step S15d: Based on the spatial distribution of drought centers, the agricultural and pastoral areas are divided into several sub-areas using Thiessen polygons, each of which contains a drought center.

4. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 1, wherein: The step S2 is further as follows: Step S21: Collecting hydrological station detection data and using cross-sectional flow calculation method to collect water flow data at different frequencies; Step S22: collecting hydrological data and water level dynamic changes, detecting water quality parameters, water quality indicators and water quantity parameters, and drawing a water layer distribution map; Step S23: Calculate the water quality rate based on the water source water quantity data and the water demand, determine the feasibility of water extraction based on the elevation difference between the water source water level and the water intake point in the irrigation area, and select the water intake; Step S24: construct surface water source engineering plans and groundwater source engineering plans based on the spatial distribution of drought centers, and combine them to obtain water source engineering layout plans for each sub-region.

5. The method for determining the scale layout of the agricultural and pastoral water network irrigation project according to claim 4, characterized in that: The step S24 is further as follows: Step S24a: Collect groundwater level monitoring data and river and lake water level data for each sub-region, draw a water level contour map based on water demand, extract the coordinates of the water level contour lines, and calculate the slope of each contour line; Step S24b: Set an initial buffer distance, generate a circular initial buffer zone with the drought center as the center, modify the initial buffer zone based on the density of water level contour lines, set a slope threshold, and divide the buffer zone into a core buffer zone and a secondary buffer zone based on the calculated contour line slopes; Step S24c: construct surface water source engineering schemes and groundwater source engineering schemes for each sub-region for the core buffer zone and the secondary buffer zone, input the pre-constructed water resources joint scheduling model, and solve the model to obtain the water source engineering layout scheme for each sub-region.

6. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 1, wherein: The step S3 is further as follows: Step S31: collecting the terrain slope of the irrigation area, the soil permeability coefficient, the distribution of crop planting areas, and the location of the water outlet of the water source project; Step S32: Select an irrigation system based on the terrain slope, and calculate the pipe diameter, dripper spacing, channel cross-sectional dimensions, and pump station head; Step S33: construct drainage projects based on the rainstorm intensity data and topographic water catchment data of each sub-region, and obtain the irrigation project layout plan for each sub-region.

7. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 1, wherein: The step S4 is further as follows: Step S41: constructing an evaluation index system, including economic value index, social benefit index and ecological benefit index; Step S42: Calculate the index value of the water network irrigation project layout plan for each sub-region respectively; Step S43: construct an economic evaluation model, extract the index values ​​of the water network irrigation project layout plan of each sub-region as the model input, calculate the comprehensive benefit score of the water network irrigation project layout plan of each sub-region, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

8. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 7, characterized in that: The step S42 is further as follows: Step S42a: Calculate economic benefit indicators using a dynamic analysis method, including net present value, internal rate of return, and payback period; Step S42b: Calculate social benefit indicators using the analytic hierarchy process, including: quality of life, employment opportunities, and social stability; Step S42c: Calculate the ecological benefit index using the ecological environment quality index method.

9. The method for determining the scale layout of a water network irrigation project in an agricultural and pastoral area according to claim 7, wherein: The step S43 is further as follows: Step S43a: Construct a multi-level comprehensive evaluation model, including a target layer, a criterion layer, and an indicator layer. The target layer is the comprehensive benefits of the scale layout plan of the agricultural and pastoral water network irrigation project. The criterion layer includes economic benefits, social benefits, and ecological benefits. The indicator layer is further subdivided according to the criterion layer. Step S43b: perform pairwise comparison and scoring of the importance of indicators based on the 1-9 scale method, construct a judgment matrix, calculate the eigenvector and maximum eigenroot of the judgment matrix, perform consistency test, determine the weight of each indicator and configure a multi-level comprehensive evaluation model; Step S43c: extract the index values ​​of the water network irrigation project layout plan of each sub-region as the input of the multi-level comprehensive evaluation model, calculate the comprehensive benefit score of the water network irrigation project layout plan of each sub-region, and the one with the highest score is the scale layout plan of the water network irrigation project in the agricultural and pastoral areas.

10. The system for determining the scale and layout of water network irrigation projects in agricultural and pastoral areas is characterized by: include: at least one processor; as well as a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the method for determining the scale layout of water network irrigation projects in agricultural and pastoral areas as described in any one of claims 1 to 9.

Images