Irrigation water consumption and canal system water utilization efficiency estimation method, device and equipment

Abstract

The invention relates to the field of agricultural water resource management, in particular to a method, device and equipment for estimating irrigation water consumption and canal system water utilization efficiency, and the method comprises the steps: screening extreme meteorological and hydrological data meeting extreme rainfall scene conditions from historical meteorological data and hydrological data, calculating label data representing moisture storage and discharge capacity of an underground water change zone by combining net exchange flux at a deep soil boundary in an extreme rainfall scene, and constructing a space-time variable specific yield estimation model by combining a machine learning algorithm based on dynamic nonlinear influence and spatial heterogeneity of the extreme rainfall scene on soil moisture; training a specific yield estimation model by using the data set carrying the label data; and based on the dynamic similar characteristics of the soil moisture in the extreme rainfall scene and the irrigation scene, migrating the trained specific yield estimation model to the irrigation scene so as to estimate the irrigation water consumption and the canal system water utilization efficiency. Therefore, the problem of how to improve the parameter accuracy of the arid region is solved.

Description

Technical Field

[0001] The present application relates to the field of agricultural water resources management, and in particular to a method, device and equipment for estimating irrigation water consumption and canal water utilization efficiency. Background Art

[0002] Agriculture accounts for about 70% of global freshwater withdrawals, of which about 90% is used for irrigation. Although irrigated agriculture accounts for less than 20% of the world's cultivated land, it contributes about 40% of food production. In my country, irrigated area accounts for 55% of cultivated land, and the average annual water use accounts for about 56% of the country's total water use, producing 77% of food and more than 90% of cash crops. With the rapid growth of population and the intensification of climate change, the demand for agricultural irrigation water is expected to increase, especially in arid irrigation areas where rainfall usually cannot meet the needs of crop growth. Therefore, accurate estimation of irrigation water is of great significance for precise management of agricultural water use, optimization of agricultural water resources allocation and ensuring food security.

[0003] Traditional monitoring methods such as water meter measurement and manual surveys have problems such as data non-disclosure, poor temporal and spatial accuracy, and time-consuming and labor-intensive, making it difficult to accurately reflect the amount of water used for farmland irrigation in large areas. Therefore, many indirect estimation methods have emerged, which can be divided into three categories: (1) integrating artificially designed irrigation modules into hydrological models, agricultural models, or land surface models, usually by artificially setting irrigation thresholds or satisfying soil moisture deficits for estimation; (2) using remote sensing technology to estimate through evapotranspiration, soil water or other hydrological elements combined with the principle of water balance; (3) using the sensitivity of soil water to external water input and the similarity between rainfall and irrigation scenarios, calibrating the model during rainfall and applying it to irrigation scenarios. These methods have provided technical support for quantifying farmland irrigation to varying degrees.

[0004] However, each method also has limitations, especially in arid irrigated areas where in situ monitoring data are relatively scarce. First, observational data in arid areas are scarce, especially soil moisture observations that are sensitive to irrigation activities, and scarce data are usually difficult to support model requirements. Second, although remote sensing can provide continuous spatiotemporal observations, its observation depth is limited to the surface, which oversimplifies or even ignores the movement of water deep in the soil, a process that is particularly important in areas with shallow groundwater depths. Finally, rainfall in arid areas is much lower than irrigation, and parameter calibration based on typical rainfall scenarios can easily lead to serious underestimations. Although it is theoretically feasible to use the similarities between rainfall and irrigation, the significant differences between the two may introduce uncertainties in arid and semi-arid areas. Summary of the invention

[0005] The present application provides a method, device and equipment for estimating irrigation water consumption and canal water utilization efficiency, so as to solve the problems that the traditional monitoring method has scarce observation data, the observation depth is limited to the surface, and the parameter calibration based on typical rainfall scenarios easily leads to the serious underestimation of parameters in arid areas.

[0006] The first embodiment of the present application provides an irrigation water consumption and canal water utilization efficiency estimation method, comprising the following steps: obtaining historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area; screening extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios from the historical meteorological data and hydrological data, and calculating and determining the various hydrological elements required to establish a water balance equation under extreme rainfall scenarios; calculating the number of tags that characterize the water storage and discharge capacity of the groundwater fluctuation zone based on the extreme meteorological and hydrological data and the net exchange flux at the deep soil boundary under extreme rainfall scenarios. A data set is generated based on label data, extreme meteorological and hydrological data, vegetation data, terrain data, soil texture data and land use data; based on the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity, a spatiotemporal and temporal variable water supply estimation model is constructed in combination with a machine learning algorithm, and the data set is used to train the water supply estimation model; based on the similar characteristics of soil moisture dynamics under extreme rainfall scenarios and irrigation scenarios, the trained water supply estimation model is migrated to the irrigation scenario, and the irrigation water consumption of the target irrigation area is estimated, and the canal water utilization efficiency is estimated based on the irrigation water consumption and water diversion volume of the target irrigation area.

[0007] Optionally, the historical meteorological and hydrological data and the extreme meteorological and hydrological data include at least one of the rainfall in the target irrigation area, potential evapotranspiration, actual evapotranspiration, soil moisture content, groundwater depth and water diversion amount in the irrigation area; the vegetation data include the leaf area index of the target irrigation area; the terrain data include at least one of the elevation and slope of the target irrigation area; and the soil texture data include at least one of the proportions of sand, clay and silt in the soil of the target irrigation area.

[0008] Optionally, after obtaining the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area, it also includes: resampling and reprojecting the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data to obtain resampled and reprojected data, wherein all resampled and reprojected data are located in the same target coordinate system and have the same spatiotemporal resolution.

[0009] Optionally, calculating and determining various hydrological elements required to establish a water balance equation under extreme rainfall scenarios includes: establishing a soil water balance equation under extreme rainfall scenarios; inputting extreme meteorological and hydrological data into the soil water balance equation under extreme rainfall scenarios, wherein the soil water balance equation under extreme rainfall scenarios outputs a net exchange amount at a soil boundary under extreme rainfall scenarios, wherein the calculation formula of the soil water balance equation under extreme rainfall scenarios is:

[0010] NEF=P-ET-ΔW ZM ,

[0011]

[0012] Where NEF represents the net exchange at the soil boundary, which represents the regional soil water storage capacity; W SM Indicates the regional soil water storage; ΔW SM represents the change in regional soil water storage during the calculation period; P represents the rainfall under extreme rainfall scenarios; ET represents actual evapotranspiration; n represents the number of soil layers; θ i Indicates the average volumetric moisture content of each soil layer; h i Represents the depth of each soil layer; NEF represents the net exchange at the soil boundary. By default, a positive value represents a downward flux, and a negative value represents an upward flux. The groundwater fluctuation equation NEF = μ × ΔH is used to estimate NEF, where μ represents the water supply degree and ΔH represents the change in groundwater depth.

[0013] Optionally, the tag data is calculated using the groundwater wave equation, using the formula:

[0014]

[0015] Among them, μ represents label data, which characterizes the water storage and discharge capacity of the groundwater fluctuation zone, and the meanings of other variables are the same as those of the above variables.

[0016] Optionally, based on the similar characteristics of soil moisture dynamics in extreme rainfall scenarios and irrigation scenarios, the trained water supply estimation model is migrated to the irrigation scenario, and the irrigation water consumption of the target irrigation area is estimated, including: historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data are input into the water supply estimation model, and the water supply estimation model outputs the spatiotemporal dynamic distribution of the water supply of the target irrigation area within the target period; the net exchange flux at the deep soil boundary is calculated point by point based on the spatiotemporal dynamic distribution of the water supply and the groundwater depth distribution, and the spatiotemporal distribution of the net exchange volume in the target irrigation area within the target period is determined based on the net exchange flux calculated point by point; the total amount of water entering the soil is estimated based on the spatiotemporal distribution of the net exchange volume, and the irrigation water consumption is obtained based on the total amount of water entering the soil and the rainfall in the target irrigation area.

[0017] Optionally, estimating the total amount of water entering the soil based on the spatiotemporal distribution of the net exchange amount includes: establishing a soil water balance equation under a non-extreme rainfall scenario; inputting the spatiotemporal distribution of the net exchange amount into the soil water balance equation under the non-extreme rainfall scenario, and the soil water balance equation under the non-extreme rainfall scenario outputs the total amount of water entering the soil, wherein the calculation formula of the soil water balance equation under the non-extreme rainfall scenario is:

[0018] ΔW SM =P+I-ET-NEF

[0019] Among them, I represents the amount of irrigation water flowing from the final channel to the field, and the meanings of the other variables are the same as the above variables.

[0020] Optionally, the canal water utilization efficiency is estimated based on the irrigation water consumption and water diversion volume of the target irrigation area, including: performing temporal and spatial data processing on the irrigation water consumption of the target irrigation area to obtain irrigation water consumption with consistent temporal and spatial resolution, and performing time series accumulation on the annual scale for the irrigation water consumption with consistent temporal and spatial resolution to obtain irrigation water consumption at the annual scale and irrigation area scale; the canal water utilization efficiency is estimated based on the irrigation water consumption at the annual scale and irrigation area scale and the water diversion volume of the target irrigation area.

[0021] The second embodiment of the present application provides an irrigation water consumption and canal water utilization efficiency estimation device, including: an acquisition module, used to acquire historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area; a determination module, used to screen extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios from historical meteorological data and hydrological data, and calculate and determine the various hydrological elements required to establish a water balance equation under extreme rainfall scenarios; a calculation module, used to calculate a label that characterizes the water storage and discharge capacity of the groundwater fluctuation zone based on the extreme meteorological and hydrological data and the net exchange flux at the deep soil boundary under extreme rainfall scenarios Data, generating data sets based on label data, extreme meteorological and hydrological data, vegetation data, terrain data, soil texture data and land use data; modeling module, based on the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity, combining machine learning algorithms to build a spatiotemporal variable water supply estimation model, and using data sets to train the water supply estimation model; estimation module, based on the similar characteristics of soil moisture dynamics under extreme rainfall scenarios and irrigation scenarios, migrating the trained water supply estimation model to irrigation scenarios, estimating the irrigation water consumption of the target irrigation area, and estimating the canal water utilization efficiency based on the irrigation water consumption and water diversion volume of the target irrigation area.

[0022] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the irrigation water consumption and canal water utilization efficiency estimation method of the first aspect.

[0023] Therefore, this application includes the following beneficial effects:

[0024] The embodiment of the present application selects extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios from historical meteorological and hydrological data, vegetation and topographic data, and soil and land data, determines the soil water storage and change, and calculates the label data that characterizes the water storage and discharge capacity of the groundwater change zone, generates a data set from the above data, constructs a spatiotemporal variable water supply estimation model under the irrigation scenario, and uses the data set to train the water supply estimation model, and finally uses the trained water supply estimation model to estimate the irrigation water consumption of the target irrigation area, and estimates the canal water utilization efficiency from the two, overcoming the estimation bias caused by the serious mismatch between rainfall and irrigation in the arid irrigation area in the existing research, accurately describing the spatiotemporal variation characteristics of water supply and net water exchange at the deep soil boundary, and realizing the irrigation water consumption estimation with high spatiotemporal resolution in large-scale areas, thereby improving the utilization efficiency of water resources, alleviating the problem of water resource shortage, and providing technical support for the sustainable development of agriculture. Thus, the problems of scarce observation data in traditional monitoring methods, observation depth limited to the surface, and parameter calibration based on typical rainfall scenarios that easily lead to serious underestimation of parameters in arid areas are solved.

[0025] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1 A flow chart of a method for estimating irrigation water consumption and canal water utilization efficiency provided according to an embodiment of the present application;

[0028] Figure 2 A flowchart of a method for estimating irrigation water consumption and canal water utilization efficiency in arid areas based on extreme rainfall scenarios according to one embodiment of the present application;

[0029] Figure 3 A schematic diagram of model accuracy results in an extreme rainfall scenario provided according to an embodiment of the present application;

[0030] Figure 4 A schematic diagram of the spatiotemporal distribution of deep soil net exchange capacity provided according to an embodiment of the present application;

[0031] Figure 5 A schematic diagram of the spatiotemporal distribution of irrigation water consumption according to an embodiment of the present application;

[0032] Figure 6 A schematic diagram of a canal water efficiency estimation result provided according to an embodiment of the present application;

[0033] Figure 7 This is a block diagram of an example of an irrigation water consumption and canal water utilization efficiency estimation device provided according to an embodiment of the present application;

[0034] Figure 8 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0036] The following describes the irrigation water consumption and canal water utilization efficiency estimation method, device and equipment of the embodiment of the present application with reference to the accompanying drawings. In view of the problems mentioned in the above background technology that the traditional monitoring method has scarce observation data, the observation depth is limited to the surface, and the parameter calibration based on typical rainfall scenarios easily leads to the serious underestimation of parameters in arid areas, the present application provides an irrigation water consumption and canal water utilization efficiency estimation method. In this method, extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios are screened from historical meteorological and hydrological data, vegetation topographic data and soil and land data to determine the soil water storage and change, and calculate the label data that characterizes the water storage and discharge capacity of the groundwater variation zone. The above data generate a data set to construct an irrigation water storage and canal water utilization efficiency estimation method. A spatiotemporal variable water supply estimation model was developed under irrigation scenarios, and the water supply estimation model was trained using the data set. Finally, the trained water supply estimation model was used to estimate the irrigation water consumption of the target irrigation area. The two were used to estimate the water utilization efficiency of the canal system, overcoming the estimation bias caused by the serious mismatch between rainfall and irrigation in arid irrigation areas in existing studies. The spatiotemporal variation characteristics of water supply and net water exchange at the deep soil boundary were accurately described, and the irrigation water consumption estimation with high spatiotemporal resolution in large-scale areas was achieved, thereby improving the utilization efficiency of water resources, alleviating the problem of water shortage, and providing technical support for the sustainable development of agriculture. As a result, the problems of scarce observation data in traditional monitoring methods, observation depth limited to the surface, and parameter calibration based on typical rainfall scenarios that easily lead to serious underestimation of parameters in arid areas were solved.

[0037] Specifically, Figure 1 A flow chart of a method for estimating irrigation water consumption and canal water utilization efficiency provided in an embodiment of the present application.

[0038] like Figure 1As shown, the method for estimating irrigation water consumption and canal water utilization efficiency includes the following steps:

[0039] In step S101, historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area are obtained.

[0040] Among them, the historical meteorological and hydrological data, vegetation topographic data, and soil and land data of the target irrigation area can be obtained from the databases of the meteorological bureau, hydrological station and other institutions in the region.

[0041] It is understandable that the embodiments of the present application can obtain historical meteorological and hydrological data, vegetation topographic data, and soil and land data of the target irrigation area by consulting the databases of the meteorological bureau, hydrological station, and other institutions in the region.

[0042] In an embodiment of the present application, the historical meteorological data and hydrological data and the extreme meteorological and hydrological data all include at least one of the rainfall in the target irrigation area, potential evapotranspiration, actual evapotranspiration, soil moisture content, groundwater depth and water diversion amount in the irrigation area; the vegetation data includes the leaf area index of the target irrigation area; the terrain data includes at least one of the elevation and slope of the target irrigation area; and the soil texture data includes at least one of the proportions of sand, clay and silt in the soil of the target irrigation area.

[0043] Among them, rainfall refers to the accumulated precipitation in a certain period; potential evapotranspiration refers to the maximum amount of water that can theoretically be removed from the surface through evaporation and plant transpiration without water restrictions; actual evapotranspiration refers to the amount of water actually lost from the soil and plant system through evaporation and transpiration; soil moisture content refers to the water content in the soil; groundwater depth refers to the distance from the groundwater surface to the ground; irrigation area water diversion refers to the amount of water introduced from the water source into the irrigation system; leaf area index refers to half of the total leaf area per unit surface area, which is used to measure vegetation density; the elevation of the target irrigation area refers to the height of the ground in the target irrigation area relative to the reference plane (such as sea level); the slope of the target irrigation area refers to the angle of inclination of the surface of the target irrigation area; the proportion of sand, clay and silt in the soil reflects the distribution of soil particle size and determines the texture of the soil; land use data describes the different uses of land, such as cultivated land, forest, construction land, etc.

[0044] It can be understood that historical meteorological and hydrological data and extreme meteorological and hydrological data may include rainfall in the target irrigation area, potential evapotranspiration, actual evapotranspiration, soil moisture content, groundwater depth and irrigation area water diversion; vegetation topography data include leaf area index of the target irrigation area, elevation and slope of the target irrigation area or more; soil land data include the proportion of sand, clay and silt in the soil of the target irrigation area and one or more of the land use data; the meteorological and hydrological conditions of the target irrigation area are determined by the above quantities.

[0045] In an embodiment of the present application, after obtaining the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area, it also includes: resampling and reprojecting the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data to obtain resampled and reprojected data, wherein all resampled and reprojected data are located in the same target coordinate system and have the same spatiotemporal resolution.

[0046] Among them, reprojection is the process of converting data from one coordinate system to another; resampling refers to the process of changing the spatial resolution of raster data; the processed data are located in the same target coordinate system and have the same spatiotemporal resolution, which is conducive to comparison and comprehensive analysis.

[0047] It can be understood that after the embodiment of the present application obtains the historical meteorological and hydrological data, vegetation topographic data and soil and land data of the target irrigation area, it is necessary to resample and reproject the acquired data, and convert the above data into a set of data with the same temporal and spatial resolution in the same target coordinate system to ensure the consistency of data of different dimensions, so as to facilitate subsequent processing and analysis of the data.

[0048] It is worth mentioning that the site data in the data need additional interpolation processing. Site data refers to data collected through various monitoring sites. These sites are usually in fixed locations, and there may be unmeasured areas between the sites. Interpolation processing can estimate the data values ​​of these unmeasured areas, thereby filling the spatial gaps.

[0049] In step S102, extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios are screened from historical meteorological and hydrological data, and various hydrological elements required to establish a water balance equation under extreme rainfall scenarios are calculated and determined.

[0050] Among them, extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios are screened from historical meteorological and hydrological data, and the judgment criteria for extreme rainfall are determined by statistical methods. Potential extreme rainfall events are determined by comparing rainfall with the judgment criteria, and spatial consistency screening conditions are used to avoid the interference of irrigation on water dynamics, eliminate local rainfall in small areas, analyze the spatial distribution data in the target irrigation area, and screen out rainfall events that widely cover the entire area, and finally obtain extreme rainfall scenarios that meet the conditions; the method for determining the regional soil water storage capacity and change amount under extreme rainfall scenarios will be described in detail below and will not be repeated here.

[0051] It can be understood that the embodiment of the present application screens historical meteorological and hydrological data through statistical methods and spatial consistency screening conditions, and selects rainfall events that widely cover the entire region and have rainfall exceeding the judgment criteria, that is, extreme meteorological and hydrological data of extreme rainfall scene conditions, and determines the regional soil water storage and change under extreme rainfall scenarios based on these data.

[0052] In an embodiment of the present application, the calculation determines the hydrological elements required to establish a water balance equation under an extreme rainfall scenario, including: establishing a soil water balance equation under the extreme rainfall scenario; inputting the extreme meteorological and hydrological data into the soil water balance equation under the extreme rainfall scenario, wherein the soil water balance equation under the extreme rainfall scenario outputs the net exchange amount at the soil boundary under the extreme rainfall scenario, wherein the calculation formula of the soil water balance equation under the extreme rainfall scenario is:

[0053] NEF=P-ET-ΔW SM ,

[0054]

[0055] Where NEF represents the net exchange at the soil boundary, which represents the regional soil water storage capacity; W SM Indicates the regional soil water storage; ΔW SM represents the change in regional soil water storage during the calculation period; P represents the rainfall under extreme rainfall scenarios; ET represents actual evapotranspiration; n represents the number of soil layers; θ i Indicates the average volumetric moisture content of each soil layer; h i Represents the depth of each soil layer; NEF represents the net exchange at the soil boundary. By default, a positive value represents a downward flux, and a negative value represents an upward flux. The groundwater fluctuation equation NEF = μ × ΔH is used to estimate NEF, where μ represents the water supply degree and ΔH represents the change in groundwater depth.

[0056] It can be understood that through the above formula, the change in regional soil water storage within a period of time can be calculated from the rainfall in extreme rainfall scenarios, the actual evapotranspiration, and the net exchange volume at the soil boundary; the regional soil water storage can be calculated by the average volumetric moisture content of each soil layer and the depth of each soil layer.

[0057] In step S103, label data characterizing the water storage and discharge capacity of the groundwater fluctuation zone is calculated based on extreme meteorological and hydrological data and the net exchange flux at the deep soil boundary under extreme rainfall scenarios, and a data set is generated based on the label data, extreme meteorological and hydrological data, vegetation data, terrain data, soil texture data and land use data.

[0058] The calculation of the label data will be described in detail below and will not be repeated here.

[0059] It can be understood that the embodiments of the present application can obtain extreme meteorological and hydrological data and regional soil water storage and changes under extreme rainfall scenarios, and calculate label data characterizing the water storage and discharge capacity of the groundwater variation zone based on the above data, and generate a data set for model training by using label data, extreme meteorological and hydrological data, vegetation terrain data and soil land data.

[0060] In the embodiment of the present application, the tag data is calculated by the groundwater wave equation, and the calculation formula is:

[0061]

[0062] Among them, μ represents label data, which characterizes the water storage and discharge capacity of the groundwater fluctuation zone, and the meanings of other variables are the same as those of the variables in step S102.

[0063] It can be understood that the embodiments of the present application can calculate label data through the change in regional soil water storage within a time period, the rainfall in extreme rainfall scenarios, the actual evapotranspiration and the change in groundwater depth, which can be used to train machine learning models.

[0064] In step S104, based on the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity, a spatiotemporally variable water supply estimation model is constructed in combination with a machine learning algorithm, and the water supply estimation model is trained using the data set.

[0065] Among them, the similar characteristics of soil moisture dynamics under extreme rainfall scenarios and irrigation scenarios refer to the fact that both extreme rainfall scenarios and irrigation are large-scale water input events that occur in a short period of time for the land, and the two have similar characteristics on soil moisture dynamics; the impact of extreme rainfall scenarios on soil moisture dynamics is nonlinear. For example, when the soil is not yet saturated, a small amount of precipitation may be quickly absorbed by the soil. When the soil is close to saturation, further precipitation will be more converted into runoff or infiltration; the spatial heterogeneity of extreme rainfall scenarios on soil moisture dynamics refers to the fact that factors such as soil type, vegetation cover, and topography in different locations will lead to significant differences in soil moisture response.

[0066] It can be understood that the spatiotemporally variable water supply estimation model under the irrigation scenario of the embodiment of the present application is constructed based on the similar characteristics of soil moisture dynamics in extreme rainfall scenarios and irrigation scenarios, the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity, and the model is trained using the generated data set including multi-source data variables, which fully considers the complexity of soil moisture changes and rainfall scenarios.

[0067] In an embodiment of the present application, the trained water supply estimation model is migrated to the irrigation scenario based on similar characteristics of soil moisture dynamics in extreme rainfall scenarios and irrigation scenarios, and the irrigation water consumption of the target irrigation area is estimated, including: inputting the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data into the water supply estimation model, and the water supply estimation model outputs the spatiotemporal dynamic distribution of the water supply of the target irrigation area within the target period; calculating the net exchange flux at the deep soil boundary point by point hourly according to the spatiotemporal dynamic distribution of the water supply and the groundwater depth distribution, and determining the spatiotemporal distribution of the net exchange amount in the target irrigation area within the target period according to the net exchange flux calculated point by point hourly; estimating the total amount of water entering the soil according to the spatiotemporal distribution of the net exchange amount, and obtaining the irrigation water consumption according to the total amount of water entering the soil and the rainfall in the target irrigation area.

[0068] Among them, the spatiotemporal dynamic distribution of water supply refers to the change in the ability of the soil to allow water to pass through at different times and spatial positions within the target period; the time-by-time and point-by-point calculation means that each time point and each spatial position is calculated one by one, which can capture subtle changes in time and space; the net exchange flux at the deep soil boundary refers to the net inflow or outflow between the water in the soil and the groundwater at the junction of the soil and groundwater; the spatiotemporal distribution of the net exchange volume is estimated by multiplying the water supply distribution by the groundwater depth distribution, and calculated time-by-time and point-by-point.

[0069] It can be understood that the embodiment of the present application utilizes the trained water supply estimation model, inputs historical meteorological and hydrological data, vegetation topographic data, and soil and land data, and can obtain the spatiotemporal dynamic distribution of the water supply of the target irrigation area within the target period. Combined with the groundwater depth distribution, the net exchange flux at the deep soil boundary can be calculated. The calculation is performed time by time, and each time point and each spatial position are calculated one by one. The subtle changes in time and space can be captured. The calculated net exchange flux can determine the spatiotemporal distribution of the net exchange volume in the target irrigation area within the target period, so that the total amount of water entering the soil can be estimated based on the spatiotemporal distribution of the net exchange volume, and finally the irrigation water consumption can be determined together with the precipitation.

[0070] In an embodiment of the present application, the total amount of water entering the soil is estimated based on the spatiotemporal distribution of the net exchange amount, including: establishing a soil water balance equation under a non-extreme rainfall scenario; inputting the spatiotemporal distribution of the net exchange amount into the soil water balance equation under the non-extreme rainfall scenario, and the soil water balance equation under the non-extreme rainfall scenario outputs the total amount of water entering the soil, wherein the calculation formula of the soil water balance equation under the non-extreme rainfall scenario is:

[0071] ΔW SM =P+I-ET-NEF

[0072] Among them, I represents the amount of irrigation water flowing from the final channel to the field, and the meanings of the other variables are the same as those in step S102.

[0073] It can be understood that the embodiments of the present application can substitute the rainfall under extreme rainfall scenarios, actual evapotranspiration, net exchange flux at the deep soil boundary and net exchange amount at the soil boundary into the formula for calculation to obtain an irrigation water consumption distribution consistent with the spatiotemporal resolution of the input data.

[0074] In step S105, based on the similar characteristics of soil moisture dynamics in extreme rainfall scenarios and irrigation scenarios, the trained water supply estimation model is migrated to the irrigation scenario, and the irrigation water consumption of the target irrigation area is estimated. The canal water utilization efficiency is estimated based on the irrigation water consumption and water diversion volume of the target irrigation area.

[0075] Among them, canal water utilization efficiency refers to the utilization efficiency achieved by the water transported through the canal in the irrigation system when it reaches the field and is effectively utilized by crops.

[0076] It can be understood that the embodiment of the present application can estimate the irrigation water consumption of the target irrigation area through the trained water supply estimation model, and obtain the canal water utilization efficiency through the water diversion estimation. The estimation method will be described in detail below and will not be repeated here.

[0077] In an embodiment of the present application, the canal water utilization efficiency is estimated based on the irrigation water consumption and water diversion volume of the target irrigation area, including: performing temporal and spatial data processing on the irrigation water consumption of the target irrigation area to obtain irrigation water consumption with consistent temporal and spatial resolution, and performing time series accumulation on the annual scale for the irrigation water consumption with consistent temporal and spatial resolution to obtain irrigation water consumption at the annual scale and irrigation area scale; the canal water utilization efficiency is estimated based on the irrigation water consumption at the annual scale and irrigation area scale and the water diversion volume of the target irrigation area.

[0078] Among them, the irrigation water consumption of the target irrigation area is processed in time and space to obtain the irrigation water consumption with consistent temporal and spatial resolution, in order to ensure the consistency of the data in time and space, and to facilitate analysis and calculation; the method of estimating the irrigation water consumption at the annual scale and the irrigation area scale and the water diversion amount of the target irrigation area is to calculate the ratio between the irrigation water consumption based on the annual scale and the irrigation area scale and the irrigation area water diversion amount obtained in step S101, so as to accurately estimate the canal water utilization efficiency.

[0079] It can be understood that the embodiment of the present application first processes the data in time and space to obtain the irrigation water consumption with consistent temporal and spatial resolution, thereby ensuring the consistency of the data in time and space. Then, the irrigation water consumption with consistent temporal and spatial resolution is accumulated in a time series on an annual scale to obtain the irrigation water consumption at the annual scale and the irrigation district scale, thereby ensuring the accurate characterization of the irrigation water dynamics over a long time scale. Finally, the canal water utilization efficiency is estimated based on the irrigation water consumption at the annual scale and the irrigation district scale and the water diversion volume of the target irrigation district. By comparing and analyzing the irrigation water consumption and water diversion volume in different years year by year, the dynamic change trend of the canal water utilization coefficient in a multi-year time series is revealed.

[0080] According to the method for estimating irrigation water consumption and canal water utilization efficiency proposed in the embodiment of the present application, extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios are screened from historical meteorological and hydrological data, vegetation topographic data, and soil and land data to determine the soil water storage capacity and change, and calculate label data that characterizes the water storage and discharge capacity of the groundwater variation zone. A data set is generated from the above data, a spatiotemporal variable water supply estimation model is constructed under the irrigation scenario, and the data set is used to train the water supply estimation model. Finally, the trained water supply estimation model is used to estimate the irrigation water consumption of the target irrigation area, and the canal water utilization efficiency is estimated from the two. This overcomes the estimation deviation caused by the serious mismatch between rainfall and irrigation volume in arid irrigation areas in existing studies, accurately describes the spatiotemporal variation characteristics of water supply and net water exchange at the deep soil boundary, and realizes irrigation water consumption estimation with high spatiotemporal resolution in large-scale areas, thereby improving water resource utilization efficiency, alleviating the problem of water resource shortage, and providing technical support for the sustainable development of agriculture.

[0081] The following is a further description of the method for estimating irrigation water consumption and canal water utilization efficiency through a specific embodiment. Figure 2 As shown, the specific process includes the following steps:

[0082] Step S201, obtaining meteorological and hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area, specifically includes the following sub-steps:

[0083] Step S201-1, obtaining meteorological and hydrological data, vegetation data, topographic data, soil texture data and land use data of the target irrigation area, wherein the meteorological and hydrological data include the rainfall, potential evapotranspiration, actual evapotranspiration, soil moisture content, groundwater depth, and irrigation area water diversion of the target irrigation area, the vegetation data includes the leaf area index of the target irrigation area, the topographic data includes the elevation and slope of the target irrigation area, and the soil texture data includes the proportion of sand, clay and silt in the soil of the target irrigation area. In the embodiment, the rainfall data and groundwater depth data are site data, and the remaining data are remote sensing data.

[0084] Step S201-2: resample and reproject the above data to obtain raster data with the same temporal and spatial resolution in the same target coordinate system, wherein the rainfall raster data is obtained in advance by radial basis function interpolation, and the groundwater depth raster data is obtained in advance by Kriging function interpolation.

[0085] Step S202, through the rainfall data obtained in step S201, extreme rainfall scenes are screened out based on statistical analysis and meteorological indicators, and the similar characteristics of soil moisture dynamics under extreme rainfall scenes and irrigation scenes are used. The nonlinear impact and spatial heterogeneity of extreme rainfall scenes on soil moisture dynamics are comprehensively considered to construct a spatiotemporal variable water supply estimation model integrating a machine learning algorithm, which specifically includes the following sub-steps:

[0086] Step S202-1: Screening of extreme rainfall scenes:

[0087] Based on the rainfall data collected in step S201-1, the daily rainfall sequence of the target irrigation area during the study period is extracted and arranged in descending order by rainfall. The criterion for determining extreme rainfall is determined by statistical methods, and the 95% quantile in the subsequence where the rainfall is not 0 is set as the extreme rainfall threshold. On this basis, if the rainfall in the target irrigation area on a certain day exceeds the threshold, it is marked as a potential extreme rainfall event. In order to ensure that no irrigation activities occur during the rainfall event, a spatial consistency screening condition is further introduced to minimize the interference of irrigation on water dynamics. Among all potential extreme rainfall events, local rainfall in small areas is eliminated, and rainfall events that cover the entire area are screened out by analyzing the spatial distribution data in the target irrigation area, that is, rainfall is recorded at all monitoring points within the entire irrigation area. Finally, an extreme rainfall scenario that meets the conditions is obtained.

[0088] Step S203: Acquisition of machine learning labels:

[0089] According to the water balance principle, the soil water balance equation under the extreme rainfall scenario screened in step S202-1 is established, which can be expressed as:

[0090] ΔW SM =P-ET-NEF (1)

[0091]

[0092] Among them, W SM Indicates the regional soil water storage; ΔW SM represents the change in regional soil water storage during the calculation period; P represents the rainfall under extreme rainfall scenarios; ET represents actual evapotranspiration; n represents the number of soil layers; θ i Indicates the average volumetric moisture content of each soil layer; h irepresents the depth of each soil layer; NEF represents the net exchange at the soil boundary. By default, a positive value indicates a downward flux, and a negative value indicates an upward flux. For ease of calculation, the groundwater wave equation is used to estimate NEF, as shown in formula (3).

[0093] NEF=μ×ΔH (3)

[0094] Among them, μ represents the water supply degree; ΔH represents the change in groundwater depth.

[0095] The label of water supply degree is estimated by the soil water balance equation, as shown in formula (4):

[0096]

[0097] Based on the evapotranspiration, rainfall, soil water storage, and groundwater depth data under the selected extreme rainfall scenarios, the water supply value of the corresponding pixel is estimated as the label of the model.

[0098] Step S204: constructing a water supply degree estimation model based on machine learning:

[0099] A water supply estimation model was constructed based on the random forest algorithm. The training input data included multi-source data variables, which fully considered the complexity of soil moisture changes and rainfall scenarios, including actual evapotranspiration, potential evapotranspiration, soil water storage changes, surface soil moisture content, deep soil moisture content, leaf area index, groundwater depth changes, elevation data, slope, land use type identification, and soil texture (the proportion of sand, clay, and silt) under extreme rainfall scenarios. All input data were standardized before entering the model to ensure the consistency of data of different dimensions. Water supply μ was used as label data for model training. The data set was divided into training set, test set, and validation set in a ratio of 6:2:2. By training the random forest model and continuously optimizing the hyperparameters, the optimal parameter combination was finally found, so that the model can extract implicit nonlinear relationships from complex multi-source data. After the model was trained, it was evaluated on the test set and validation set using R 2 , mean square error (MAE) and root mean square error (RMSE) to evaluate the accuracy and generalization ability of the model. Figure 3 As shown, it shows that the model effectively captures the complex nonlinear relationship between water supply degree and its influencing factors, and realizes the spatiotemporal dynamic inversion of water supply degree parameters.

[0100] Step S205, based on the high spatiotemporal resolution water supply estimation model trained in step S202, estimates the net water exchange flux in the deep soil layer, and combines the soil water balance equation to accurately estimate the total amount of water entering the soil, deducting the regional rainfall to quantify the irrigation water consumption, which specifically includes the following sub-steps:

[0101] Step S205-1: Application of water supply model:

[0102] All actual evapotranspiration, potential evapotranspiration, soil water storage change, surface soil moisture content, deep soil moisture content, leaf area index, groundwater depth change, elevation data, slope, land use type identification, and soil texture data during the study period are used as input data for the model established in step S202-3. The spatiotemporal dynamic distribution of the water supply degree of the target irrigation area during the study period is calculated through the trained spatiotemporal variable water supply degree estimation model, thereby solving the limitation of the water supply degree parameter in existing research that is usually calibrated alone.

[0103] Step S205-2: Estimation of net exchange volume:

[0104] According to formula (3), the water supply distribution obtained in step S205-1 is multiplied by the groundwater depth distribution obtained in step S201-2 to obtain the spatiotemporal distribution of the net exchange volume of the target irrigation area during the study period, as follows: Figure 4 The results show that the estimated net exchange volume in this example is consistent with the actual situation of the irrigation area where the example is located, which helps to clarify the sustainable utilization of groundwater and the utilization of irrigation return water.

[0105] Step S206: Estimation of irrigation water consumption:

[0106] According to the principle of water balance, the soil water balance equation under general circumstances can be expressed as:

[0107] ΔW SM =P+I-ET-NEF (5)

[0108] Where I represents the amount of irrigation water flowing from the final channel to the field, and the other variables have the same meaning as in formula (1). Substitute the rainfall and evapotranspiration obtained in step S201-2, the net exchange amount obtained in step S205-2, and the soil moisture content obtained in step S201-2 and the change in soil water storage obtained in formula (2) into formula (5) to obtain the irrigation water distribution consistent with the temporal and spatial resolution of the input data, as follows: Figure 5 The results can help clarify the irrigation dynamics and irrigation water use during the year, and provide guidance for agricultural water management and optimization of water resources allocation in irrigation areas.

[0109] Step S207, using the irrigation water consumption estimated in step S205 and the target irrigation area water diversion volume obtained in step S201, accurately calculate the canal water utilization efficiency through ratio analysis to effectively evaluate the water resource management efficiency of the irrigation system at the regional scale, which specifically includes the following sub-steps:

[0110] Step S207-1, data post-processing:

[0111] The irrigation water consumption estimated in step S206 is processed comprehensively in time and space. First, the irrigation water consumption with consistent temporal and spatial resolution is accumulated in time series on an annual scale to ensure accurate characterization of the dynamics of irrigation water consumption over a long time scale. Second, the spatially distributed irrigation water consumption is spatially aggregated within the region and aggregated to a specific regional point scale to provide a more macro regional scale irrigation water consumption estimation result for subsequent analysis.

[0112] Step S207-2, estimation of canal water utilization coefficient:

[0113] Based on the irrigation water consumption at the annual scale and irrigation area scale, the ratio between it and the irrigation area water diversion volume obtained in step S201-1 is calculated to accurately estimate the canal water utilization efficiency. This ratio reflects the water loss from the canal head to the field in the irrigation area water transmission and distribution system. By comparing and analyzing the irrigation water consumption and water diversion volume in different years year by year, the dynamic change trend of the canal water utilization coefficient in a multi-year time series is revealed, such as Figure 6 shown.

[0114] In summary, firstly, the embodiment of the present application utilizes the similarity between extreme rainfall events and irrigation processes in terms of water dynamics to construct a deep soil water exchange estimation model, and successfully migrates it to irrigation scenarios. This innovative method effectively solves the problem of serious mismatch between rainfall and irrigation in arid areas, and provides a new solution for areas lacking irrigation data. Secondly, this embodiment fully considers the water exchange process between saturated and unsaturated zones in deep soil, especially the return and reuse of groundwater recharge, discharge and groundwater evaporation, which enhances the comprehensive understanding of regional hydrological processes. At the same time, this embodiment combines multi-source remote sensing data and hydro-meteorological factors to fully explore the complex nonlinear relationship between these data and irrigation water consumption. By training the model with machine learning technology, it can estimate the spatiotemporal distribution of irrigation water consumption with high precision and continuously, and significantly improve the analysis accuracy of canal water utilization efficiency in arid areas. Its powerful nonlinear fitting ability and data migration ability make the model highly versatile in different regions and conditions. This embodiment has important practical value, and can provide strong technical support and decision-making basis for water resource management, agricultural irrigation planning and sustainable utilization of groundwater resources in arid areas, and provide reliable basic data support for the subsequent establishment of distributed hydrological models in irrigation areas, thereby further improving the scientificity and effectiveness of water resource management in arid areas.

[0115] Next, the irrigation water consumption and canal water utilization efficiency estimation device proposed in the embodiment of the present application is described with reference to the accompanying drawings.

[0116] Figure 7 It is a block diagram of an irrigation water consumption and canal water utilization efficiency estimation device according to an embodiment of the present application.

[0117] like Figure 7 As shown, the irrigation water consumption and canal water utilization efficiency estimation device 10 includes: an acquisition module 301 , a determination module 302 , a calculation module 303 , a modeling module 304 and an estimation module 305 .

[0118] Among them, the acquisition module 301 is used to obtain the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area; the determination module 302 is used to screen the extreme meteorological and hydrological data that meet the conditions of the extreme rainfall scene from the historical meteorological data and hydrological data, and calculate and determine the various hydrological elements required to establish the water balance equation under the extreme rainfall scene; the calculation module 303 is used to calculate the label data representing the water storage and discharge capacity of the groundwater fluctuation zone according to the extreme meteorological and hydrological data and the net exchange flux at the deep soil boundary under the extreme rainfall scene, and calculate the label data representing the water storage and discharge capacity of the groundwater fluctuation zone according to the label data, the extreme meteorological and hydrological data The data set is generated based on the vegetation data, the terrain data, the soil texture data and the land use data; the modeling module 304 is used to build a spatiotemporally variable water supply estimation model based on the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity in combination with a machine learning algorithm, and the water supply estimation model is trained using the data set; the estimation module 305 is used to migrate the trained water supply estimation model to the irrigation scenario based on the similar characteristics of soil moisture dynamics under extreme rainfall scenarios and irrigation scenarios, and estimate the irrigation water consumption of the target irrigation area, and estimate the canal water utilization efficiency based on the irrigation water consumption and water diversion volume of the target irrigation area.

[0119] In an embodiment of the present application, the historical meteorological data and hydrological data and the extreme meteorological and hydrological data all include at least one of the rainfall in the target irrigation area, potential evapotranspiration, actual evapotranspiration, soil moisture content, groundwater depth and water diversion amount in the irrigation area; the vegetation data includes the leaf area index of the target irrigation area; the terrain data includes at least one of the elevation and slope of the target irrigation area; and the soil texture data includes at least one of the proportions of sand, clay and silt in the soil of the target irrigation area.

[0120] In an embodiment of the present application, a processing module is also included, and the processing module is further used to: after obtaining the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data of the target irrigation area, it also includes: resampling and reprojecting the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data to obtain resampled and reprojected data, wherein all resampled and reprojected data are located in the same target coordinate system and have the same spatiotemporal resolution.

[0121] In the embodiment of the present application, the determination module 302 is further used to: establish a soil water balance equation under the extreme rainfall scenario; input the extreme meteorological and hydrological data into the soil water balance equation under the extreme rainfall scenario, and the soil water balance equation under the extreme rainfall scenario outputs the net exchange amount at the soil boundary under the extreme rainfall scenario, wherein the calculation formula of the soil water balance equation under the extreme rainfall scenario is:

[0122] NEF=P-ET-ΔW SM ,

[0123]

[0124] Where NEF represents the net exchange at the soil boundary, which represents the regional soil water storage capacity; W SM Indicates the regional soil water storage; ΔW SM represents the change in regional soil water storage during the calculation period; P represents the rainfall under extreme rainfall scenarios; ET represents actual evapotranspiration; n represents the number of soil layers; θ i Indicates the average volumetric moisture content of each soil layer; h i Represents the depth of each soil layer; NEF represents the net exchange at the soil boundary. By default, a positive value represents a downward flux, and a negative value represents an upward flux. The groundwater fluctuation equation NEF = μ × ΔH is used to estimate NEF, where μ represents the water supply degree and ΔH represents the change in groundwater depth.

[0125] In the embodiment of the present application, the tag data is calculated by the groundwater wave equation, and the calculation formula is:

[0126]

[0127] Among them, μ represents label data, which characterizes the water storage and discharge capacity of the groundwater fluctuation zone, and the meanings of other variables are the same as those of the above variables.

[0128] In an embodiment of the present application, the estimation module 305 is further used to: input the historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data into the water supply estimation model, and the water supply estimation model outputs the spatiotemporal dynamic distribution of the water supply of the target irrigation area within the target period; calculate the net exchange flux at the deep soil boundary point by point hourly according to the spatiotemporal dynamic distribution of the water supply and the groundwater depth distribution, and determine the spatiotemporal distribution of the net exchange amount in the target irrigation area within the target period according to the net exchange flux calculated point by point hourly; estimate the total amount of water entering the soil according to the spatiotemporal distribution of the net exchange amount, and obtain the irrigation water consumption according to the total amount of water entering the soil and the rainfall in the target irrigation area.

[0129] In an embodiment of the present application, the total amount of water entering the soil is estimated according to the spatiotemporal distribution of the net exchange amount, including: establishing a soil water balance equation under a non-extreme rainfall scenario; inputting the spatiotemporal distribution of the net exchange amount into the soil water balance equation under the non-extreme rainfall scenario, and the soil water balance equation under the non-extreme rainfall scenario outputs the total amount of water entering the soil, wherein the calculation formula of the soil water balance equation under the non-extreme rainfall scenario is:

[0130] ΔW SM =P+I-ET-NEF

[0131] Among them, I represents the amount of irrigation water flowing from the final channel to the field, and the meanings of the other variables are the same as the above variables.

[0132] In an embodiment of the present application, the estimation module 305 is further used to: perform temporal and spatial data processing on the irrigation water consumption of the target irrigation area to obtain an irrigation water consumption with consistent temporal and spatial resolution, and perform time series accumulation on the annual scale on the irrigation water consumption with consistent temporal and spatial resolution to obtain the irrigation water consumption at the annual scale and the irrigation area scale; estimate the canal water utilization efficiency based on the irrigation water consumption at the annual scale and the irrigation area scale and the water diversion volume of the target irrigation area.

[0133] It should be noted that the above explanations of the embodiment of the method for estimating the irrigation water consumption and canal water utilization efficiency are also applicable to the device for estimating the irrigation water consumption and canal water utilization efficiency of this embodiment, and will not be repeated here.

[0134] According to the irrigation water consumption and canal water utilization efficiency estimation device proposed in the embodiment of the present application, through the synergistic effect of the acquisition module, the determination module, the calculation module, the modeling module and the estimation module, it is possible to screen extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios from historical meteorological and hydrological data, vegetation and topographic data and soil and land data, determine the soil water storage capacity and change, and calculate the label data representing the water storage and discharge capacity of the groundwater variation zone, generate a data set from the above data, construct a spatiotemporal variable water supply estimation model under the irrigation scenario, and use the data set to train the water supply estimation model, and finally use the trained water supply estimation model to estimate the irrigation water consumption of the target irrigation area, and use the two to estimate the canal water utilization efficiency, thereby overcoming the estimation deviation caused by the serious mismatch between rainfall and irrigation volume in arid irrigation areas in existing studies, accurately describing the spatiotemporal variation characteristics of water supply and net water exchange at the deep soil boundary, and realizing irrigation water consumption estimation with high spatiotemporal resolution in large-scale areas, thereby improving water resource utilization efficiency, alleviating the problem of water resource shortage, and providing technical support for the sustainable development of agriculture.

[0135] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0136] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0137] When the processor 402 executes the program, the irrigation water consumption and canal water utilization efficiency estimation method provided in the above embodiment is implemented.

[0138] Furthermore, the electronic device also includes:

[0139] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0140] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0141] The memory 401 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0142] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0143] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0144] The processor 402 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0145] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0146] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0147] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0148] It should be understood that the various parts of the present application can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, the steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0149] A person of ordinary skill in the art may understand that all or part of the steps carried by the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the above-mentioned program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0150] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for estimating irrigation water consumption and canal water utilization efficiency, characterized in that: The following steps are involved: Obtain historical meteorological data, hydrological data, vegetation data, topographic data, soil texture data, and land use data of the target irrigation area; Selecting extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios from the historical meteorological and hydrological data, and calculating and determining various hydrological elements required to establish a water balance equation under the extreme rainfall scenario; Calculating label data representing the water storage and discharge capacity of the groundwater fluctuation zone based on the extreme meteorological and hydrological data and the net exchange flux at the deep soil boundary under the extreme rainfall scenario, and generating a data set based on the label data, the extreme meteorological and hydrological data, the vegetation data, the terrain data, the soil texture data, and the land use data; Based on the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity, a spatiotemporally variable water supply estimation model is constructed in combination with a machine learning algorithm, and the water supply estimation model is trained using the data set; Based on the similar characteristics of soil moisture dynamics under extreme rainfall scenarios and irrigation scenarios, the trained water supply estimation model is migrated to the irrigation scenario, and the irrigation water consumption of the target irrigation area is estimated. The canal water utilization efficiency is estimated based on the irrigation water consumption and water diversion volume of the target irrigation area.

2. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 1, characterized in that: The historical meteorological data and hydrological data and the extreme meteorological and hydrological data include at least one of the rainfall in the target irrigation area, potential evapotranspiration, actual evapotranspiration, soil moisture content, groundwater depth and water diversion in the irrigation area; the vegetation data include the leaf area index of the target irrigation area; the terrain data include at least one of the elevation and slope of the target irrigation area; and the soil texture data include at least one of the proportions of sand, clay and silt in the soil of the target irrigation area.

3. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 1 or 2, characterized in that: After obtaining the historical meteorological data, hydrological data, vegetation data, topographic data, soil texture data and land use data of the target irrigation area, it also includes: The historical meteorological data, hydrological data, vegetation data, terrain data, soil texture data and land use data are all resampled and reprojected to obtain resampled and reprojected data, wherein all the resampled and reprojected data are located in the same target coordinate system and have the same spatiotemporal resolution.

4. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 1, characterized in that: The calculation determines the hydrological elements required to establish the water balance equation under extreme rainfall scenarios, including: Establishing a soil water balance equation under the extreme rainfall scenario; The extreme meteorological and hydrological data are input into the soil water balance equation under the extreme rainfall scenario, and the soil water balance equation under the extreme rainfall scenario outputs the net exchange amount at the soil boundary under the extreme rainfall scenario, wherein the calculation formula of the soil water balance equation under the extreme rainfall scenario is: NEF=P-ET-ΔW SM , Where NEF represents the net exchange at the soil boundary, which represents the regional soil water storage capacity; W SM Indicates the regional soil water storage; ΔW SM represents the change in regional soil water storage during the calculation period; P represents the rainfall under extreme rainfall scenarios; ET represents actual evapotranspiration; n represents the number of soil layers; θ i Indicates the average volumetric moisture content of each soil layer; h i Represents the depth of each soil layer; NEF represents the net exchange at the soil boundary. By default, a positive value represents a downward flux, and a negative value represents an upward flux. The groundwater fluctuation equation NEF = μ × ΔH is used to estimate NEF, where μ represents the water supply degree and ΔH represents the change in groundwater depth.

5. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 4, characterized in that: The tag data is calculated by the groundwater wave equation, and the calculation formula is: Among them, μ represents the label data, which characterizes the water storage and discharge capacity of the groundwater fluctuation zone.

6. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 1, characterized in that: Based on the similar characteristics of soil moisture dynamics in extreme rainfall scenarios and irrigation scenarios, the trained water supply estimation model is transferred to the irrigation scenario, and the irrigation water consumption of the target irrigation area is estimated, including: Inputting the historical meteorological data, hydrological data, vegetation data, topographic data, soil texture data and land use data into the water supply estimation model, the water supply estimation model outputs the spatiotemporal dynamic distribution of the water supply of the target irrigation area within the target period; Calculating the net exchange flux at the boundary of the deep soil layer point by point and hour by hour according to the spatiotemporal dynamic distribution of the water supply degree and the distribution of the groundwater depth, and determining the spatiotemporal distribution of the net exchange amount in the target irrigation area within the target period according to the net exchange flux calculated point by hour and hour; The total amount of water entering the soil is estimated based on the temporal and spatial distribution of the net exchange amount, and the irrigation water amount is obtained based on the total amount of water entering the soil and the rainfall in the target irrigation area.

7. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 6, characterized in that: The estimating the total amount of water entering the soil according to the spatiotemporal distribution of the net exchange amount comprises: Establish soil water balance equations under non-extreme rainfall scenarios; The spatiotemporal distribution of the net exchange amount is input into the soil water balance equation under the non-extreme rainfall scenario, and the soil water balance equation under the non-extreme rainfall scenario outputs the total amount of water entering the soil, wherein the calculation formula of the soil water balance equation under the non-extreme rainfall scenario is: ΔW SM =P+I-ET-NEF Where I represents the amount of irrigation water flowing from the final channel to the field.

8. The method for estimating irrigation water consumption and canal water utilization efficiency according to claim 1, characterized in that: The estimating the canal water utilization efficiency according to the irrigation water consumption and water diversion volume of the target irrigation area includes: Processing the irrigation water consumption of the target irrigation area in time and space to obtain the irrigation water consumption with consistent time and space resolution, and performing time series accumulation on the annual scale on the irrigation water consumption with consistent time and space resolution to obtain the irrigation water consumption at the annual scale and the irrigation area scale; The canal water utilization efficiency is estimated based on the irrigation water consumption at the annual scale and the irrigation area scale and the water diversion volume of the target irrigation area.

9. A device for estimating irrigation water consumption and canal water utilization efficiency, characterized in that: include: An acquisition module is used to acquire historical meteorological data, hydrological data, vegetation data, topographic data, soil texture data, and land use data of the target irrigation area; A determination module, used to select extreme meteorological and hydrological data that meet the conditions of extreme rainfall scenarios from the historical meteorological data and hydrological data, and calculate and determine various hydrological elements required to establish a water balance equation under extreme rainfall scenarios; a calculation module, for calculating label data representing the water storage and discharge capacity of the groundwater fluctuation zone according to the extreme meteorological and hydrological data and the net exchange flux at the deep soil boundary under the extreme rainfall scenario, and generating a data set according to the label data, the extreme meteorological and hydrological data, the vegetation data, the terrain data, the soil texture data and the land use data; A modeling module, for building a spatiotemporally variable water supply estimation model based on the nonlinear impact of extreme rainfall scenarios on soil moisture dynamics and spatial heterogeneity in combination with a machine learning algorithm, and training the water supply estimation model using the data set; The estimation module is used to migrate the trained water supply estimation model to the irrigation scenario based on the similar characteristics of soil moisture dynamics in extreme rainfall scenarios and irrigation scenarios, and estimate the irrigation water consumption of the target irrigation area, and estimate the canal water utilization efficiency based on the irrigation water consumption and water diversion volume of the target irrigation area.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for estimating irrigation water consumption and canal water utilization efficiency as described in any one of claims 1 to 8.

Images