An irrigation district canal system water distribution optimization method, system, computer device and medium

Abstract

The application provides a canal system water distribution optimization method, system, computer device and medium, and belongs to the field of agricultural informatization, and comprises the following steps: collecting multi-source remote sensing data, spectral radiation data and meteorological data; determining crop types and distribution; determining evapotranspiration from the spectral radiation data and the meteorological data; obtaining a plurality of management partitions based on the crop types and the distribution; determining the net irrigation water volume of the management partition according to the daily evapotranspiration, crop water requirement law and soil moisture availability, and then constructing a water requirement prescription map; determining an irrigation system with the crop yield maximization, the highest water use efficiency and the lowest irrigation cost as optimization objectives, the time window constraint, the crop rotation irrigation constraint and the soil moisture constraint as constraint conditions, according to the crop growth model corresponding to the crop types and the distribution and the hydrological year type determined based on the meteorological data; and then determining the canal system water distribution volume and water distribution time. The method improves the accuracy and scientificity of water distribution decision.

Description

Technical Field

[0001] This invention belongs to the field of agricultural informatization, and specifically relates to a method, system, computer equipment and medium for optimizing water distribution in irrigation canal systems. Background Technology

[0002] Canal system water allocation refers to the process in an irrigation area of ​​transporting and distributing water from reservoirs, rivers, and other sources to field irrigation units within a specific timeframe, based on crop water requirements, through a network of canals including main canals, branch canals, distribution canals, and farm canals. Its core objective is to achieve precise, efficient, and equitable allocation of water resources, meeting the water needs of different regions and crops while ensuring the safe operation of the canal system and minimizing water loss. Experience-based, extensive water allocation models cannot respond to the spatiotemporal variability of crop water needs, easily leading to water shortages in some areas and over-irrigation in others. This not only wastes water resources but also causes crop yield reduction and even soil salinization. Therefore, through scientific decision-making, the optimal allocation of limited irrigation water in time and space to achieve a comprehensive optimization of multiple objectives such as crop yield, water use efficiency, and economic benefits is an essential requirement and core means to achieve intensive and economical use of water resources, ensure irrigation benefits, and promote sustainable agricultural development.

[0003] Based on the above requirements, existing technologies utilize remote sensing evapotranspiration models such as SEBAL to invert regional evapotranspiration, thereby estimating crop water shortage and formulating optimized water allocation schemes. However, the SEBAL model estimates key parameters based on empirical relationships between "cold spots" and "hot spots" within remote sensing images, neglecting the fundamental differences in energy distribution and water transport among different crop species due to their varying canopy structures, stomatal behaviors, phenological and biophysical properties. Consequently, when dealing with irrigation areas with multiple crop rotations, existing water allocation optimization methods become disconnected from actual yield-increasing and water-saving effects, resulting in poor usability of water allocation schemes. Summary of the Invention

[0004] To address the issue of poor usability of existing water distribution schemes, this invention provides a method, system, computer equipment, and medium for optimizing water distribution in irrigation canal systems.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A method for optimizing water distribution in irrigation canal systems includes: Multi-source remote sensing data, spectral radiation data, and meteorological data of the irrigation area to be optimized were collected; vegetation index features and spectral features were extracted from the multi-source remote sensing data, and the crop types and distribution of the irrigation area to be optimized were determined from the vegetation index features and spectral features; based on the surface energy balance method, instantaneous evapotranspiration at the pixel scale was determined from the spectral radiation data and meteorological data, and the evapotranspiration of the irrigation area to be optimized was determined from the instantaneous evapotranspiration using the evaporation ratio method. Based on the crop types and distribution of the irrigation area to be optimized, the irrigation area to be optimized is divided into multiple management zones; the net irrigation amount of each management zone is determined according to the daily evapotranspiration, the water requirement pattern of the corresponding crop type and the soil moisture availability, and the water requirement prescription map of the irrigation area to be optimized is constructed from the net irrigation amount of each management zone. Based on the crop types and distribution of the irrigation area to be optimized, combined with the corresponding crop growth model and the hydrological year type determined based on meteorological data, the optimization objectives are to maximize crop yield, maximize water use efficiency, and minimize irrigation cost. The time window constraint for irrigation time is set according to the growth stage of the corresponding crop in each management interval. The crop rotation irrigation constraint is set according to the mutual exclusion of irrigation time for multiple management intervals in the irrigation area to be optimized by the same canal. The soil moisture constraint is set according to the single irrigation volume of each management interval being within the soil moisture threshold range corresponding to the crop. The irrigation system of the irrigation area to be optimized is determined. The canal water distribution volume and water distribution time of the irrigation area to be optimized are determined by the irrigation system, water demand prescription map and canal system structure of the irrigation area to be optimized.

[0006] Optionally, the irrigation district canal system water distribution optimization method provided by the present invention further includes: Spectral features are extracted from multiple bands in multi-source remote sensing data; Enhanced vegetation index and normalized vegetation index are calculated from crop vegetation index features in multi-source remote sensing data. Time series were constructed based on the enhanced vegetation index and normalized vegetation index and spectral characteristics; the crop types and distribution of the irrigation area to be optimized were determined from the time series using a pre-trained deep learning algorithm.

[0007] Optionally, the irrigation district canal system water distribution optimization method provided by the present invention further includes: Instantaneous evapotranspiration at the pixel scale is calculated based on spectral radiation data and meteorological data using the SEBAL or TESB algorithm. The instantaneous evapotranspiration was extended to a daily scale by the evaporation ratio method to obtain the daily evapotranspiration. The potential evapotranspiration of the irrigation area is determined by the FAO dual crop coefficient method, and the daily evapotranspiration is corrected based on the potential evapotranspiration to obtain the evapotranspiration of the irrigation area to be optimized.

[0008] Optionally, the irrigation district canal system water distribution optimization method provided by the present invention further includes: The aerodynamic impedance of each cell in each management zone is corrected based on the crop types and distribution of the irrigation areas to be optimized in each management zone, and the sensible heat flux of the cell is corrected based on the corrected aerodynamic impedance. The daily evapotranspiration of a pixel is calculated based on the updated sensible heat flux and soil heat flux of each pixel; the daily evapotranspiration of the management zone is determined by the daily evapotranspiration of multiple pixels.

[0009] Optionally, the irrigation district canal system water distribution optimization method provided by the present invention further includes: The daily evapotranspiration of a management zone is determined based on the average daily evapotranspiration of multiple cells in each management zone; the daily evapotranspiration of each management zone is used to classify multiple management zones into different water demand levels. The net irrigation amount for each management zone is determined based on its different water requirement levels, soil moisture availability, and water requirement patterns of the crop types within that zone.

[0010] Optionally, the irrigation district canal system water distribution optimization method provided by the present invention further includes: With the objectives of maximizing the sum of crop yields across all management zones and maximizing the ratio of the sum of crop yields to the sum of total water consumption, a multi-objective optimization function is constructed. By solving the multi-objective optimization function, the irrigation time, single irrigation volume, and number of irrigations for the irrigation area to be optimized are obtained.

[0011] Optionally, the irrigation district canal system water distribution optimization method provided by the present invention further includes: The flow allocation constraint is set to each channel based on the fact that the irrigation volume through the channel in each management zone is lower than the upper limit of the corresponding channel flow. The water supply constraint is set based on the fact that the total irrigation volume through the channel in all management zones in a single irrigation cycle is lower than the water supply threshold of the corresponding water source in the corresponding time period. The channel operation stability constraint is set based on the fact that the flow fluctuation in adjacent time intervals of each channel is less than the preset change range.

[0012] The present invention also provides an irrigation district canal system water distribution optimization system, comprising: The data acquisition module is used to collect multi-source remote sensing data, spectral radiation data, and meteorological data of the irrigation area to be optimized; extract vegetation index features and spectral features from the multi-source remote sensing data, and determine the crop types and distribution of the irrigation area to be optimized based on the vegetation index features and spectral features; determine the instantaneous evapotranspiration at the pixel scale based on the surface energy balance method, and determine the daily evapotranspiration of the irrigation area to be optimized based on the instantaneous evapotranspiration using the evaporation ratio method; The water requirement prescription map construction module is used to divide the irrigation area to be optimized into multiple management zones based on the crop types and distribution of the irrigation area to be optimized; within each management zone, the net irrigation amount is determined according to the average daily evapotranspiration, the water requirement pattern of the corresponding crop type, and the soil moisture availability; and the water requirement prescription map of the irrigation area to be optimized is constructed from the net irrigation amount of each management zone. The water allocation scheme generation module is used to determine the irrigation regime for the irrigation area to be optimized based on the crop types and distribution of the irrigation area, combined with the corresponding crop growth model and the hydrological year type determined based on meteorological data. The optimization objectives are to maximize crop yield, maximize water use efficiency, and minimize irrigation cost. The module sets time window constraints for irrigation time according to the growth stage of the corresponding crop in each management interval, sets crop rotation irrigation constraints according to the mutual exclusion of irrigation time for multiple management intervals in the irrigation area to be optimized by the same canal supply, and sets soil moisture constraints according to the single irrigation volume of each management interval being within the soil moisture threshold range corresponding to the crop. The module then determines the canal water allocation volume and water allocation time for the irrigation area to be optimized based on the irrigation regime, water demand prescription map, and canal system structure.

[0013] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement any of the steps in an irrigation district canal system water distribution optimization method.

[0014] The present invention also provides a computer-readable storage medium storing a computer program, which, when loaded by a processor, is capable of executing any step of an irrigation district canal system water distribution optimization method.

[0015] The water distribution optimization method for irrigation canal systems provided by this invention has the following beneficial effects: This invention comprehensively utilizes multi-source remote sensing, spectral, and meteorological data to accurately identify the types and spatial distribution of different crops within an irrigation area by analyzing the time series of vegetation indices and spectral characteristics. Based on this, a surface energy balance model is used to invert and obtain pixel-scale evapotranspiration, which is then extended to daily-scale data. Next, the irrigation area is divided into multiple management zones according to crop distribution. Combining the average daily evapotranspiration, crop water requirements, and soil conditions of each zone, a spatiotemporal water requirement prescription map is generated to guide differentiated irrigation in different regions. Furthermore, the scheme couples a crop growth model with a multi-objective optimization algorithm, aiming for optimal yield, water use efficiency, and cost, to solve for the optimal irrigation regime for different hydrological year types. Finally, by comprehensively integrating the optimized irrigation regime, water requirement prescription map, and actual canal topology, the specific water allocation amount and timing for each canal are determined.

[0016] This invention actively identifies crop types and distribution through remote sensing, providing crucial crop identification information for subsequent analysis. This avoids the evapotranspiration inversion mechanism errors caused by the homogenization of the underlying surface and neglect of differences in the biophysical properties of different crops in traditional methods, thus improving the physical accuracy and precision of water demand diagnosis. Furthermore, a crop growth model is introduced and coupled with multi-objective optimization. This allows irrigation regime formulation to move beyond simple estimations of instantaneous water shortages, simulating the entire growth process and final yield formation of crops under different water supply strategies. This enables predictive global optimization of crop yield increase and irrigation water-saving effects.

[0017] In summary, the irrigation canal system water allocation optimization method provided by this invention not only responds to the spatiotemporal heterogeneity of crop water demand and conforms to the physiological growth law of crops themselves, but also takes into account the constraints of the engineering system. It effectively solves the fundamental problems of existing optimization schemes being out of touch with actual agricultural production goals and having poor usability, and significantly improves the accuracy and scientific nature of water allocation decisions. Attached Figure Description

[0018] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is one of the schematic diagrams of an irrigation canal system water distribution optimization method provided by an embodiment of the present invention; Figure 2 This is a second schematic diagram of a water distribution optimization method for irrigation canal systems provided in an embodiment of the present invention; Figure 3 This is an example of an optimized water distribution process for irrigation canal systems provided in an embodiment of the present invention; Figure 4 This is the third schematic diagram of a water distribution optimization method for irrigation canal systems provided in an embodiment of the present invention; Figure 5 This is the fourth schematic diagram of a water distribution optimization method for irrigation canal systems provided in an embodiment of the present invention; Figure 6 This is an example of irrigation system optimization based on crop models provided in an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0021] Example 1 This invention provides a method for optimizing water distribution in irrigation canal systems, specifically as follows: Figure 1 As shown, it includes the following steps: Step 11: Collect multi-source remote sensing data, spectral radiation data, and meteorological data of the irrigation area to be optimized; extract vegetation index features and spectral features from the multi-source remote sensing data, and determine the crop types and distribution of the irrigation area to be optimized based on the vegetation index features and spectral features; determine the instantaneous evapotranspiration at the pixel scale based on the surface energy balance method, and determine the evapotranspiration of the irrigation area to be optimized based on the instantaneous evapotranspiration using the evaporation ratio method.

[0022] Among them, such as Figure 2 As shown, step 11 includes: Step 111: Extract spectral features from multiple bands in the multi-source remote sensing data; calculate the enhanced vegetation index and normalized vegetation index from the crop vegetation index features in the multi-source remote sensing data.

[0023] Step 112: Construct a time series based on the enhanced vegetation index and normalized vegetation index and spectral characteristics; determine the crop types and distribution of the irrigation area to be optimized from the time series using a pre-trained deep learning algorithm.

[0024] Step 113: Based on the SEBAL algorithm or TESB algorithm, calculate the instantaneous evapotranspiration at the pixel scale according to the spectral radiation data and meteorological data.

[0025] Step 114: Extend instantaneous evapotranspiration to a daily scale using the evaporation ratio method to obtain daily evapotranspiration.

[0026] Step 115: Determine the potential evapotranspiration of the irrigation area using the FAO dual crop coefficient method, and correct the daily evapotranspiration based on the potential evapotranspiration to obtain the evapotranspiration of the irrigation area to be optimized.

[0027] Specifically, such as Figure 3 As shown, for irrigation areas that require irrigation optimization, multi-source remote sensing data such as satellite data and UAV imaging data, hydrological and meteorological data such as temperature, air pressure, wind speed, and sunshine duration, as well as ground sample information data are collected. For example, ground sampling point data and visual interpretation data for different crops are obtained based on UAV measured data.

[0028] After data collection was completed, crop planting structure analysis of the irrigation area was conducted based on multi-source remote sensing data. For example, using the GEE platform, an enhanced spatial and temporal adaptive reflectance fusion model and a change-based spatiotemporal data fusion method were employed to fuse the multi-source remote sensing data from various sources, resulting in fused data with a spatial resolution of 30m and a temporal frequency of 1d. Furthermore, the fused data underwent preprocessing methods such as cloud removal, cropping, atmospheric correction, and geometric topography correction. For instance, pixels containing clouds, cirrus clouds, cloud shadows, and snow were removed pixel-by-pixel from the fused data to obtain fused data free from meteorological interference.

[0029] Then, spectral features are extracted from the preprocessed fused data, such as blue, green, red, near-infrared (NIR), shortwave infrared-1 (SWIR-1), and shortwave infrared-2 (SWIR-2) bands from the image data. Vegetation indices are then calculated based on the preprocessed fused data, using, for example, the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) as vegetation index features. Next, time-series features are constructed from the spectral and vegetation index features, and these features are input into pre-trained machine learning or deep learning algorithms such as decision tree algorithms, support vector machine algorithms, or random forest algorithms for the identification and classification of major crops, yielding the planting area and distribution of crops. Furthermore, to ensure the accuracy of the crop identification and classification structure, ground sample information data collected by UAVs can be combined to verify the overall accuracy (OA) and Kappa coefficient, achieving quantitative accuracy verification and evaluation of the automatic crop classification results. Only when both verification indicators meet preset conditions will the classification results output by deep learning determine the crop classification map of the irrigation area to be optimized.

[0030] On the other hand, the sensible heat flux and soil heat flux are calculated using the Surface Energy Balance Algorithm for Land (SEBAL) based on spectral radiance data in the visible, near-infrared, and thermal infrared portions of satellite imagery, along with basic meteorological data of the irrigation area to be optimized. This yields instantaneous evapotranspiration at the pixel scale. Subsequently, the evaporation ratio method is used to extend the obtained instantaneous evapotranspiration to a diurnal scale to obtain the daily evapotranspiration. Furthermore, to ensure the accuracy of the estimated daily evapotranspiration, flux tower observation data can be combined to calculate the root mean square error (REMS) and coefficient of determination (R²) between the observed data and the estimated daily evapotranspiration. 2 This allows for a more accurate evaluation of daily evapotranspiration. Only when both verification indicators meet the preset conditions will the results of the daily-scale expansion be used as the daily evapotranspiration of the irrigation area to be optimized.

[0031] It is important to emphasize that this invention can not only calculate instantaneous evapotranspiration using the SEBAL algorithm, but also, through the Two-Source Energy Balance model (TESB), divide the surface of the irrigation area to be optimized into a composite system consisting of two independent energy sources: the vegetation canopy and the bare soil. The energy fluxes of vegetation transpiration and soil evaporation are calculated separately, and then the two are added together to obtain the total latent heat flux at the pixel scale, i.e., instantaneous evapotranspiration. The specific calculation method is to be selected by those skilled in the art based on actual needs; this invention does not impose any limitations.

[0032] Furthermore, before calculating the net irrigation volume, step 11 also includes: Step 116: Correct the aerodynamic impedance of each cell in each management zone based on the crop types and distribution of the irrigation area to be optimized in each management zone, and then correct the sensible heat flux of the cell based on the corrected aerodynamic impedance.

[0033] Step 117: Calculate the daily evapotranspiration of each pixel based on the updated sensible heat flux and soil heat flux; determine the daily evapotranspiration of the management zone based on the daily evapotranspiration of multiple pixels.

[0034] Specifically, considering that the SEBAL model is an empirical parameterization scheme based on relative relationships within an image, its goal is to avoid dependence on absolute meteorological conditions rather than to infer the aerodynamic properties of specific crops from physical mechanisms. It cannot inversely deduce the specific crop type of a pixel from the energy balance results of a single phase or short time series. When relying solely on the SEBAL model to calculate daily evapotranspiration, different types of plants will be treated as a fuzzy, averaged "green object," resulting in inherent, non-self-eliminating mechanistic errors when inverting aerodynamic properties and biophysical parameters that are strongly correlated with crop types.

[0035] Therefore, after obtaining the crop classification map of the irrigation area to be optimized and the evapotranspiration of the irrigation area, the sensible heat flux is corrected based on the corresponding aerodynamic impedance of different types and densities of crops in the crop classification map. Then, the latent heat flux or evapotranspiration of the irrigation area to be optimized is determined by combining soil heat flux and net radiation. In addition, considering the differences in different crop types, growth cycles and densities, the soil heat flux can be corrected based on the vegetation index corresponding to different crops, and the net radiation can be corrected based on the dynamic surface albedo curve of different crops. The optimized evapotranspiration after taking into account the differences in crop type, distribution and density is obtained, which further improves the physical authenticity and accuracy of the evapotranspiration inversion process and provides a foundation for the efficient setting of subsequent water distribution schemes.

[0036] Step 12: Divide the irrigation area to be optimized into multiple management zones based on the crop types and distribution of the irrigation area to be optimized; determine the net irrigation amount of each management zone according to the daily evapotranspiration, the water requirement pattern of the corresponding crop type and the soil moisture availability, and construct the water requirement prescription map of the irrigation area to be optimized based on the net irrigation amount of each management zone.

[0037] Among them, such as Figure 4 As shown, step 12 includes: Step 121: Determine the daily evapotranspiration of each management zone based on the average daily evapotranspiration of multiple cells in each management zone; classify multiple management zones into different levels based on the daily evapotranspiration of each management zone to obtain management zones with different water demand levels.

[0038] Step 122: Determine the net irrigation amount for each management zone based on its different water requirement levels, soil moisture availability, and water requirement patterns of the crop types within that management zone.

[0039] Specifically, after obtaining the crop classification map and evapotranspiration of the irrigation area, an object-oriented multi-scale segmentation algorithm can be used to accurately manage and partition the obtained crop planting structure map. Then, a spatiotemporal prescription map of the irrigation area to be optimized can be created using ArcGIS 10.6 software. For example, firstly, the irrigation area to be optimized is segmented based on the crop classification map, resulting in multiple management zones. Then, for each management zone, the average daily evapotranspiration of each estimated cell is taken as the daily evapotranspiration of that management zone. Based on the differences in daily evapotranspiration among multiple management zones, water demand levels are classified. And based on the water demand characteristics of different crops at different stages and the soil moisture availability characteristics, the value range for each water demand level is selected. Considering different irrigation methods, corresponding net irrigation amounts are set for different management zones according to different water demand levels, and a spatiotemporal water demand prescription map is generated based on this.

[0040] Step 13: Based on the crop growth model corresponding to the crop types and distribution in the irrigation area to be optimized, and the hydrological year type determined based on meteorological data, with the optimization objectives of maximizing crop yield, maximizing water use efficiency, and minimizing irrigation cost, set time window constraints for irrigation time according to the growth stage of the corresponding crop in each management interval, set crop rotation irrigation constraints according to the mutual exclusion of irrigation time for multiple management intervals supplied by the same canal in the irrigation area to be optimized, and set soil moisture constraints according to the single irrigation volume of each management interval being within the soil moisture threshold range corresponding to the crop, and determine the irrigation regime of the irrigation area to be optimized; determine the canal water distribution volume and water distribution time of the irrigation area to be optimized based on the irrigation regime, water demand prescription map, and canal system structure of the irrigation area to be optimized.

[0041] Among them, such as Figure 5 As shown, step 13 includes: Step 131: The objective is to maximize the sum of crop yields across all management zones and the ratio of the sum of crop yields to the sum of total water consumption.

[0042] Step 132: Set the flow allocation constraint to each channel based on the fact that the irrigation volume through the channel in each management interval is lower than the upper limit of the corresponding channel flow. Set the water supply constraint based on the fact that the total irrigation volume through the channel in all management intervals in a single irrigation cycle is lower than the water supply threshold of the corresponding water source in the corresponding time period. Set the channel operation stability constraint based on the fact that the flow fluctuation in adjacent time intervals of each channel is less than the preset change range.

[0043] Step 133: Solve the multi-objective optimization function to obtain the irrigation time, single irrigation amount, and number of irrigations for the irrigation area to be optimized.

[0044] Specifically, after the spatial-temporal water demand prescription map is constructed, typical hydrological years, such as wet years, normal years, and dry years, are defined for the irrigation area to be optimized based on spatial gridded rainfall data and high-resolution meteorological data. Based on these typical hydrological years, crop growth models such as the APSIM model and multi-objective optimization algorithms such as NSGA-II are coupled to generate an irrigation regime optimization model suitable for the management interval scale. Then, with the optimization objectives of maximizing yield, maximizing water use efficiency, and minimizing irrigation costs, the irrigation regime for the irrigation area to be optimized is solved. Finally, by combining the water demand prescription map, the controlled area of ​​the canal system, crop types, and the optimal irrigation regime for the crops, the optimal water allocation and timing for the canal system are determined, thereby achieving optimization of the irrigation area's canal system water allocation.

[0045] The multi-objective optimization algorithm can aim to maximize the sum of crop yields across all management zones, achieve the highest water use efficiency by setting the ratio of yield to total water consumption across all management zones, and minimize irrigation costs by setting the total water consumption and total irrigation time across all management zones. Alternatively, the differences in the economic value of crops across different management zones can be considered to determine their weights in the multi-objective optimization. Furthermore, to reduce the computational burden of the multi-objective optimization algorithm, it can be transformed into a single-objective optimization algorithm by setting weights for each objective. In this case, the weights corresponding to the minimum irrigation cost objective can be set to negative values, and the optimal irrigation regime can be determined by finding the irrigation regime corresponding to the maximum value.

[0046] Furthermore, to prevent the canal system from overflowing due to excessive flow, flow allocation constraints can be used to limit the flow of each canal to less than the corresponding overflow limit; to prevent excessive water pumping from affecting the sustainable development of water resources in water-scarce areas, water supply constraints can be used to limit the total amount of water pumped from reservoirs, rivers, or groundwater in a single irrigation cycle or throughout the entire growing season; to prevent drastic fluctuations in canal water levels and flow and to ensure the safety and stability of water delivery, canal operation stability constraints can be used to set limits on the variation of flow or water level in adjacent time periods within the canal.

[0047] Furthermore, in multi-objective optimization algorithms, constraints can be set to ensure that the needs of different types of crops are met. For example, a time window constraint can be set for the critical period of crop water demand, defining a hard time window for irrigation that must be implemented for each crop in the irrigation area to be optimized, such as the flowering period and the grain-filling period. In addition, the propagation time of water flow from the canal head to the field can be set in combination with the canal system structure, thereby ensuring that irrigation water can reach the corresponding crops within the window period and avoid affecting the normal growth of crops. In addition, based on the canal system topology, mutually exclusive irrigation time constraints can be set for different field groups supplied by the same canal to achieve orderly rotation irrigation and avoid unnecessary peaks in canal flow demand, which would increase the workload of the canal system. Moreover, when there are multiple water sources with different water qualities, such as fresh water and reclaimed water with different salinity contents, the usage ratio or time period of different water qualities can be set in combination with the salt tolerance of the corresponding crops and the salt and alkali resistance of the corresponding soil, forming constraints on water quality mixing or usage sequence, thereby reducing the overall irrigation cost. Dynamic soil moisture constraints can also be set for different crop types. For example, different upper limits for soil moisture can be set for different crops to prevent waterlogging, and lower limits for soil moisture can be set as irrigation trigger points to ensure that the soil moisture in the crop root zone is always within its suitable range, thereby further ensuring the normal growth of crops.

[0048] And, as Figure 6 As shown, the present invention also provides an example of optimized water distribution in irrigation canal systems: First, obtain meteorological data such as temperature, rainfall, wind speed, and solar radiation for the irrigation area to be optimized; soil data such as soil type, soil bulk density, soil wilting coefficient, and field water holding capacity; experimental data determined in advance, such as crop LAI / CC, crop biomass, and crop yield; and irrigation quota data such as irrigation method, irrigation time, and irrigation water volume determined based on the canal system of the irrigation area to be optimized.

[0049] Secondly, based on the aforementioned meteorological, soil, experimental, and irrigation quota data, the crop growth model undergoes localization. For example, since crop growth models typically contain dozens or even hundreds of parameters, a global sensitivity analysis is first used to identify a few parameters that have the greatest impact on key outputs such as local crop yield and water consumption as sensitivity coefficients. Then, using the sensitive parameters identified in the previous step as optimization variables, and taking field observation data on biomass, final yield, and soil moisture dynamics at different growth stages in the irrigation area to be optimized as the target, optimization algorithms such as genetic algorithms are used to automatically search for a set of parameter values ​​that best match the model simulation results with the observed values, thus completing the calibration of crop parameters in the crop growth model. Finally, the calibrated crop growth model is tested using field trial data from different irrigation or water treatments. By verifying whether the model can accurately simulate the crop's growth response and final yield under different water stresses, the crop growth model is calibrated and validated, thereby achieving localization of the crop growth model.

[0050] Furthermore, based on the localized crop growth model, crop planting structure analysis and evapotranspiration inversion were performed on the irrigation areas to be optimized to obtain the crop classification map and crop evapotranspiration of the irrigation areas to be optimized, and then the water demand prescription map of the irrigation areas to be optimized was constructed.

[0051] Subsequently, based on long-term meteorological data of the irrigation area to be optimized, hydrological year types such as high-water years, normal-water years, and low-water years were defined. Combined with collected data and water demand prescription maps, these were input into an optimization architecture coupling the AquaCrop crop growth model and the NSGA-II multi-objective optimization algorithm. The optimization objective was to achieve the optimal balance between crop yield and water use efficiency at the research scale of the irrigation area. Different irrigation regime schemes were generated and iterated using the NSGA-II algorithm, and the AquaCrop model was used to simulate the final yield and water use efficiency of each scheme. The optimization algorithm continuously evaluated and selected schemes until the iteration termination condition was met, ultimately outputting a Pareto optimal solution set containing a series of optimized irrigation regimes that were not superior in terms of yield and water use efficiency. Then, based on the actual decision preferences of the irrigation area to be optimized, an irrigation regime scheme was determined from the Pareto optimal solution set as the optimal irrigation regime.

[0052] Finally, by combining the optimal irrigation system, the irrigation time and irrigation water volume of the irrigation area to be optimized are determined, and an irrigation plan is prepared to complete the optimization of the canal system water distribution in the irrigation area to be optimized.

[0053] Example 2 The present invention also provides an irrigation district canal system water distribution optimization system, comprising: The data acquisition module is used to collect multi-source remote sensing data, spectral radiation data, and meteorological data of the irrigation area to be optimized; extract vegetation index features and spectral features from the multi-source remote sensing data, and determine the crop types and distribution of the irrigation area to be optimized based on the vegetation index features and spectral features; determine the instantaneous evapotranspiration at the pixel scale based on the surface energy balance method, and determine the daily evapotranspiration of the irrigation area to be optimized based on the instantaneous evapotranspiration using the evaporation ratio method; The water requirement prescription map construction module is used to divide the irrigation area to be optimized into multiple management zones based on the crop types and distribution of the irrigation area to be optimized; within each management zone, the net irrigation amount is determined according to the average daily evapotranspiration, the water requirement pattern of the corresponding crop type, and the soil moisture availability; and the water requirement prescription map of the irrigation area to be optimized is constructed from the net irrigation amount of each management zone. The water allocation scheme generation module is used to determine the irrigation regime for the irrigation area to be optimized based on the crop growth model corresponding to the crop types and distribution of the irrigation area to be optimized, as well as the hydrological year type determined based on meteorological data. The optimization objectives are to maximize crop yield, maximize water use efficiency, and minimize irrigation cost. The module sets time window constraints for irrigation time according to the growth stage of the corresponding crop in each management interval, sets crop rotation irrigation constraints according to the mutual exclusion of irrigation time for multiple management intervals in the irrigation area to be optimized by the same canal supply, and sets soil moisture constraints according to the single irrigation volume of each management interval being within the soil moisture threshold range corresponding to the crop. The module then determines the canal water allocation volume and water allocation time for the irrigation area to be optimized based on the irrigation regime, water demand prescription map, and canal system structure of the irrigation area to be optimized.

[0054] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps in an embodiment of a method for optimizing water distribution in an irrigation canal system. Specific implementation methods can be found in the method embodiments, and will not be repeated here.

[0055] Furthermore, the present invention also provides a non-transitory computer-readable storage medium containing instructions, on which a computer program is stored. For example, a memory containing instructions that can be executed by a processor of a computer device to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the computer program is executed by the processor, it can implement the steps in an embodiment of a method for optimizing water distribution in an irrigation canal system. Specific implementation methods can be found in the method embodiments, which will not be repeated here.

[0056] Those skilled in the art will understand that embodiments of the present invention can provide methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0057] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0058] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0059] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0060] It should be noted that the specific embodiments described above enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification and embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the present invention patent. No reference numerals in the claims should be construed as limiting the scope of the claims. Any simple variations or equivalent substitutions of technical solutions that can be readily obtained by those skilled in the art within the scope of the technology disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for optimizing water distribution in an irrigation canal system, characterized in that, include: Collect multi-source remote sensing data, spectral radiation data, and meteorological data of the irrigation area to be optimized; Vegetation index features and spectral features are extracted from the multi-source remote sensing data. The crop types and distribution of the irrigation area to be optimized are determined from the vegetation index features and spectral features. Based on the surface energy balance method, the instantaneous evapotranspiration at the pixel scale is determined from the spectral radiation data and meteorological data. The evapotranspiration of the irrigation area to be optimized is determined from the instantaneous evapotranspiration using the evaporation ratio method. Based on the crop types and distribution of the irrigation area to be optimized, the irrigation area to be optimized is divided into multiple management zones; the net irrigation amount of each management zone is determined according to the daily evapotranspiration, the water requirement pattern of the corresponding crop type and the soil moisture availability, and the water requirement prescription map of the irrigation area to be optimized is constructed from the net irrigation amount of each management zone. Based on the crop types and distribution of the irrigation area to be optimized, combined with the corresponding crop growth model and the hydrological year type determined based on meteorological data, the optimization objectives are to maximize crop yield, maximize water use efficiency, and minimize irrigation cost. The time window constraint for irrigation time is set according to the growth stage of the corresponding crop in each management interval. The crop rotation irrigation constraint is set according to the mutual exclusion of irrigation time for multiple management intervals supplied by the same canal in the irrigation area to be optimized. The soil moisture constraint is set according to the single irrigation volume of each management interval being within the soil moisture threshold range corresponding to the crop. The irrigation system of the irrigation area to be optimized is determined. The canal water distribution volume and water distribution time of the irrigation area to be optimized are determined by the irrigation system, water demand prescription map and canal system structure of the irrigation area to be optimized.

2. The method for optimizing water distribution in an irrigation canal system according to claim 1, characterized in that, Vegetation index features and spectral features are extracted from the multi-source remote sensing data. The crop types and distribution of the irrigation area to be optimized are determined based on the vegetation index features and spectral features, including: The spectral features are extracted from multiple bands in the multi-source remote sensing data; the enhanced vegetation index and the normalized vegetation index are calculated from the crop vegetation index features in the multi-source remote sensing data. A time series is constructed based on the enhanced vegetation index and normalized vegetation index and spectral characteristics; the crop types and distribution of the irrigation area to be optimized are determined from the time series using a pre-trained deep learning algorithm.

3. The method for optimizing water distribution in an irrigation canal system according to claim 1, characterized in that, Instantaneous evapotranspiration at the pixel scale is determined from the spectral radiation data and meteorological data. The evapotranspiration of the irrigation area to be optimized is then determined from the instantaneous evapotranspiration using the evaporation ratio method, including: Instantaneous evapotranspiration at the pixel scale is calculated based on the SEBAL or TESB algorithm and the spectral radiation data and meteorological data. The instantaneous evapotranspiration was extended to a daily scale using the evaporation ratio method to obtain the daily evapotranspiration. The potential evapotranspiration of the irrigation area is determined by the FAO dual crop coefficient method, and the daily evapotranspiration is corrected based on the potential evapotranspiration to obtain the evapotranspiration of the irrigation area to be optimized.

4. The method for optimizing water distribution in an irrigation canal system according to claim 1, characterized in that, Before determining the net irrigation volume for this management zone, the following steps are also included: The aerodynamic impedance of each cell in each management zone is corrected based on the crop types and distribution of the irrigation areas to be optimized in each management zone, and the sensible heat flux of the cell is corrected based on the corrected aerodynamic impedance. The daily evapotranspiration of a pixel is calculated based on the updated sensible heat flux and soil heat flux of each pixel; the daily evapotranspiration of the management zone is determined by the daily evapotranspiration of multiple pixels.

5. The method for optimizing water distribution in an irrigation canal system according to claim 4, characterized in that, The net irrigation amount for each management zone is determined based on its daily evapotranspiration, the water requirement patterns of the corresponding crop types, and the availability of soil moisture. The daily evapotranspiration of a management zone is determined based on the average daily evapotranspiration of multiple cells in each management zone; the multiple management zones are classified into different levels based on the daily evapotranspiration of each management zone to obtain management zones with different water demand levels. The net irrigation amount for each management zone is determined based on its different water requirement levels, soil moisture availability, and water requirement patterns of the crop types within that zone.

6. The method for optimizing water distribution in an irrigation canal system according to claim 1, characterized in that, Optimization objectives that maximize crop yield, maximize water use efficiency, and minimize irrigation costs include: With the objectives of maximizing the sum of crop yields across all management zones and maximizing the ratio of the sum of crop yields to the sum of total water consumption, a multi-objective optimization function is constructed. By solving the multi-objective optimization function, the irrigation time, single irrigation volume, and number of irrigations for the irrigation area to be optimized are obtained.

7. The method for optimizing water distribution in an irrigation canal system according to claim 6, characterized in that, With the optimization objectives of maximizing crop yield, maximizing water use efficiency, and minimizing irrigation costs, the irrigation regimes for the irrigation district to be optimized are determined to include: The flow allocation constraint is set to each channel based on the fact that the irrigation volume through the channel in each management zone is lower than the upper limit of the corresponding channel flow. The water supply constraint is set based on the fact that the total irrigation volume through the channel in all management zones in a single irrigation cycle is lower than the water supply threshold of the corresponding water source in the corresponding time period. The channel operation stability constraint is set based on the fact that the flow fluctuation in adjacent time intervals of each channel is less than the preset change range.

8. A water distribution optimization system for irrigation canal systems, characterized in that, include: The data acquisition module is used to collect multi-source remote sensing data, spectral radiation data, and meteorological data of the irrigation area to be optimized; Vegetation index features and spectral features are extracted from the multi-source remote sensing data. The crop types and distribution of the irrigation area to be optimized are determined from the vegetation index features and spectral features. Based on the surface energy balance method, the instantaneous evapotranspiration at the pixel scale is determined from the spectral radiation data and meteorological data. The daily evapotranspiration of the irrigation area to be optimized is determined from the instantaneous evapotranspiration using the evaporation ratio method. The water requirement prescription map construction module is used to divide the irrigation area to be optimized into multiple management zones based on the crop types and distribution of the irrigation area to be optimized; within each management zone, the net irrigation amount of the management zone is determined according to the average daily evapotranspiration, the water requirement pattern of the corresponding crop type, and the soil moisture availability; and the water requirement prescription map of the irrigation area to be optimized is constructed from the net irrigation amount of each management zone. The water allocation scheme generation module is used to determine the irrigation regime of the irrigation area to be optimized based on the crop types and distribution of the irrigation area to be optimized, combined with the corresponding crop growth model and the hydrological year type determined based on meteorological data. The optimization objectives are to maximize crop yield, maximize water use efficiency, and minimize irrigation cost. The module sets time window constraints for irrigation time according to the growth stage of the corresponding crop in each management interval, sets crop rotation irrigation constraints according to the mutual exclusion of irrigation time for multiple management intervals supplied by the same canal in the irrigation area to be optimized, and sets soil moisture constraints according to the single irrigation volume of each management interval being within the soil moisture threshold range corresponding to the crop. The module then determines the canal water allocation volume and water allocation time of the irrigation area to be optimized based on the irrigation regime, water demand prescription map, and canal system structure of the irrigation area to be optimized.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the irrigation district canal system water distribution optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is loaded by the processor, it is able to execute the steps of the irrigation district canal system water distribution optimization method according to any one of claims 1 to 7.

Images