Method and system for predicting irrigation district water requirement based on long-term and short-term meteorological data

Abstract

The application discloses a long-term and short-term meteorological data-based irrigation area water demand prediction method and system, and relates to the field of irrigation area water demand prediction; the method comprises the following steps: constructing a short-term and long-term hydrological cycle conceptual mechanism model; obtaining short-term climate information according to future weather forecasts; inputting the short-term climate information into the trained short-term hydrological cycle conceptual mechanism model to obtain short-term water demand of a target irrigation area; selecting 12 CMIP6 data sets suitable for the target irrigation area to obtain long-term climate information; and inputting the long-term climate information into the trained long-term hydrological cycle conceptual mechanism model to obtain long-term water demand of the target irrigation area. The application predicts short-term and long-term water demand of the irrigation area based on short-term and long-term meteorological information, and provides a reference for short-term water resource allocation and long-term planning and construction of the irrigation area.

Description

Technical Field

[0001] This invention relates to the field of irrigation area water demand prediction, and in particular to a method and system for predicting irrigation area water demand based on long-term and short-term meteorological data. Background Technology

[0002] The construction of smart irrigation districts is an important branch of smart water conservancy. The ability to predict the short-term and long-term water demand of irrigation districts is the foundation of smart irrigation district construction and an important reference for planning watershed water resource allocation and realizing watershed-scale smart water conservancy construction.

[0003] Due to changes in crop planting structure, actual water inflow, and irrigation district management models, the actual irrigation systems in many irrigation districts in my country differ to varying degrees from the planned irrigation systems. Therefore, calculations of irrigation district water demand based on the irrigation system may contain significant errors compared to actual water demand. Furthermore, as climate change continues to alter factors such as water inflow, irrigated area, planting structure, and irrigation technology levels, irrigation district water demand will also change accordingly. Therefore, forecasting irrigation district water demand can significantly reduce the uncertainty of these changes. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for predicting water demand in irrigation areas based on long-term and short-term meteorological data, which can accurately predict the water demand of irrigation areas based on long-term and short-term meteorological data.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] A method for predicting irrigation district water demand based on long-term and short-term meteorological data, comprising:

[0007] Construct a conceptual mechanism model for the short-term hydrological cycle and a conceptual mechanism model for the long-term hydrological cycle;

[0008] Obtain short-term weather forecast data for the target irrigation area based on future weather forecasts;

[0009] Short-term climate information is obtained based on the aforementioned future short-term weather forecast data;

[0010] The short-term climate information is input into the trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area.

[0011] Twelve CMIP6 datasets applicable to the target irrigation area were selected to obtain average monthly future meteorological data from multiple datasets;

[0012] Long-term climate information is obtained based on the monthly-scale future meteorological data;

[0013] The long-term climate information is input into the trained long-term hydrological cycle conceptual mechanism model to obtain the long-term water demand of the target irrigation area.

[0014] Optionally, the step of obtaining short-term weather forecast data for the target irrigation area based on future weather forecasts further includes:

[0015] Obtain crop planting data; the crop planting data includes: historical actual daily irrigation water volume in the irrigation area and historical short-term weather forecast data;

[0016] Based on the aforementioned historical short-term weather forecast data, historical short-term climate information is obtained;

[0017] The historical short-term climate information is input into the short-term hydrological cycle conceptual mechanism model to obtain the predicted historical daily crop water demand;

[0018] The daily water demand error is obtained by comparing the predicted historical daily crop water demand with the historical actual daily irrigation water volume in the irrigation area.

[0019] The short-term hydrological cycle conceptual mechanism model is trained based on the daily water demand error to obtain the trained short-term hydrological cycle conceptual mechanism model.

[0020] Optionally, the short-term climate information includes at least: reference evapotranspiration and daily precipitation absorption;

[0021] The reference evaporation rate is calculated using the following formula:

[0022]

[0023] Among them, ET 0r For reference evaporation rate; R nr The historical average daily net solar radiation (MJ·m) -2 ·d -1 G r Historical daily average soil heat flux (MJ·m) -2 ·d -1 ;Δ r The average slope of the historical daily saturated vapor pressure-temperature curve (kg·Pa·℃) -1 ;γ r The hygrometer constant is kg·Pa·℃ -1 ;u 2r The average wind speed at a height of 2m on historical days (m·s) -1 ;e sr The average daily saturated vapor pressure in historical data (kPa); e ar The average historical daily water vapor pressure (kPa); T r The historical average temperature at a height of 2m is ℃;

[0024] The formula for the daily precipitation absorption is:

[0025]

[0026] Where P0 is the daily precipitation absorption, P r The historical daily average precipitation in mm, i mr This represents the historical maximum soil infiltration rate in mm.

[0027] Optionally, the long-term climate information includes at least: monthly average crop evapotranspiration during the growing season and monthly average precipitation absorption during the growing season;

[0028] The formula for the average monthly crop evapotranspiration during the growing season is:

[0029]

[0030] Among them, ET 0y R is the average monthly crop evapotranspiration during the growing season. ny The average monthly net solar radiation of that year (MJ·m) -2 ·d -1 G y The average monthly soil heat flux (MJ·m) for that year -2 ·d -1 ;Δ y The average slope of the monthly saturated water vapor pressure-temperature curve (kg·Pa·℃) -1 ;γ y The hygrometer constant is kg·Pa·℃ -1 ;u 2y The average wind speed at a height of 2m in that month (m·s) -1 ;e sy The average monthly saturated vapor pressure (kPa) for that year; e ay The average value of the actual monthly water vapor pressure in that year (kPa); T y The average temperature at a height of 2m in that month was °C.

[0031] The formula for the average monthly precipitation absorption during the growing season is:

[0032]

[0033] Where P1 is the average monthly precipitation absorption during the growing season, P y i represents the average monthly precipitation in mm for that year. my The maximum soil infiltration rate in that year is measured in mm.

[0034] A water demand prediction system for irrigation districts based on long-term and short-term meteorological data, wherein the water demand prediction system for irrigation districts based on long-term and short-term meteorological data is applied to the method, and the water demand prediction system for irrigation districts based on long-term and short-term meteorological data includes:

[0035] The model building module is used to build short-term and long-term hydrological cycle conceptual mechanism models.

[0036] The short-term climate information acquisition module is used to obtain future short-term weather forecast data for the target irrigation area based on future weather forecasts; and to obtain short-term climate information based on the future short-term weather forecast data.

[0037] The short-term water demand determination module is used to input the short-term climate information into the trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area.

[0038] The long-term climate information acquisition module is used to select 12 CMIP6 datasets applicable to the target irrigation area, obtain monthly-scale future meteorological data averaged across multiple datasets, and obtain long-term climate information based on the monthly-scale future meteorological data.

[0039] The long-term water demand determination module is used to input the long-term climate information into the trained long-term hydrological cycle conceptual mechanism model to obtain the long-term water demand of the target irrigation area.

[0040] Optionally, the short-term climate information acquisition module may further include a model training module.

[0041] The model training module specifically includes:

[0042] The crop planting data acquisition module is used to acquire crop planting data; the crop planting data includes: historical actual daily irrigation water volume in the irrigation area and historical short-term weather forecast data;

[0043] The historical short-term climate information determination module is used to obtain historical short-term climate information based on the historical short-term weather forecast data.

[0044] The module for determining the historical daily crop water requirement is used to input the historical short-term climate information into the short-term hydrological cycle conceptual mechanism model to obtain the first predicted historical daily crop water requirement.

[0045] The daily water demand error determination module is used to obtain the first daily water demand error based on the first predicted historical daily crop water demand and the historical actual daily irrigation water volume of the irrigation area.

[0046] The module for determining the short-term hydrological cycle conceptual mechanism model after training is used to train the short-term hydrological cycle conceptual mechanism model based on the water demand error of the first day, so as to obtain the trained short-term hydrological cycle conceptual mechanism model.

[0047] A computer-readable storage medium storing a computer program that, when executed, implements the method described above.

[0048] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described above.

[0049] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0050] This invention discloses a method and system for predicting irrigation area water demand based on short-term and long-term meteorological data. The method includes: constructing short-term and long-term hydrological cycle conceptual mechanism models; obtaining short-term climate information based on future weather forecasts; inputting the short-term climate information into the trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area; selecting 12 CMIP6 datasets suitable for the target irrigation area to obtain long-term climate information; and inputting the long-term climate information into the trained long-term hydrological cycle conceptual mechanism model to obtain the long-term water demand of the target irrigation area. This invention provides short-term and long-term predictions of irrigation area water demand based on short-term and long-term meteorological information. These predictions can also provide important references for short-term water resource allocation and long-term irrigation area water conservancy facility planning and construction, respectively. The adaptive irrigation area water demand calculation model, which combines historical irrigation area conditions and meteorological data with machine learning intelligent algorithms, can calculate irrigation area water demand more accurately than traditional methods. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, 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.

[0052] Figure 1 The flowchart illustrates the irrigation area water demand prediction method based on long-term and short-term meteorological data provided in the embodiments of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] The purpose of this invention is to provide a method and system for predicting irrigation area water demand based on short-term and long-term meteorological data, which can make short-term and long-term predictions of irrigation area water demand using short-term and long-term meteorological data, respectively.

[0055] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] Example 1

[0057] like Figure 1 As shown, this embodiment of the invention provides a method for predicting irrigation area water demand based on long-term and short-term meteorological data. The method includes:

[0058] Construct a conceptual mechanism model for the short-term hydrological cycle and a conceptual mechanism model for the long-term hydrological cycle.

[0059] In practice, the construction of short-term and long-term hydrological cycle conceptual mechanism models includes, beforehand, preparing relevant data on crop planting, historical meteorology, and historical irrigation water demand in the irrigation area. The current year's and historical crop planting data includes: crop types, planting area, crop coefficients at different growth stages, soil infiltration capacity, and soil saturation water content; historical meteorological data includes: daily average temperature, maximum temperature, minimum temperature, sunshine duration, relative humidity, precipitation, and average wind speed; historical irrigation water demand refers to the actual daily irrigation water volume in the irrigation area in history.

[0060] Current research indicates that the main factors influencing crop water requirements are precipitation and reference evapotranspiration (ETO). Reference evapotranspiration is primarily a water output from farmland, while farmland evapotranspiration mainly consists of soil evaporation and plant transpiration. This invention uses the well-established Penman-Monteith formula to estimate reference evapotranspiration; precipitation is primarily a water input to farmland. However, during short-duration heavy rainfall, if the rainfall intensity exceeds the soil's maximum infiltration capacity, the precipitation will not enter the soil and will be lost as surface runoff. Therefore, this invention sets a threshold based on the soil characteristics of the irrigation area, using the soil's infiltration capacity as the threshold. Rainfall exceeding the soil's infiltration capacity will be ignored. According to the hydrological cycle process of the irrigation area, crops are mainly affected by precipitation and evapotranspiration. Historical climate information is used as the input for irrigation water under natural conditions. Based on these natural conditions, a short-term hydrological cycle conceptual mechanism model and a long-term hydrological cycle conceptual mechanism model are constructed.

[0061] The short-term weather forecast data for the target irrigation area is obtained based on future weather forecasts.

[0062] Short-term climate information is obtained based on future short-term weather forecast data.

[0063] Short-term climate information is input into a trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area.

[0064] In practical applications, short-term climate information for the next 7 days (daily average temperature, maximum temperature, minimum temperature, sunshine duration, relative humidity, precipitation, and average wind speed) is input into the trained short-term hydrological cycle conceptual mechanism model, which outputs short-term water demand. This leads to the predicted water demand for the irrigation district for the next 7 days.

[0065] Twelve CMIP6 datasets applicable to the target irrigation area were selected to obtain monthly-scale future meteorological data averaged across multiple datasets.

[0066] Long-term climate information is obtained from future meteorological data on a monthly scale.

[0067] By inputting long-term climate information into a trained long-term hydrological cycle conceptual mechanism model, the long-term water demand of the target irrigation district can be obtained. This model can simulate the long-term water demand of the irrigation district under different future greenhouse gas emission scenarios.

[0068] In practical applications, 12 CMIP6 data points applicable to the irrigation area are selected to obtain average monthly future meteorological data (2030-2099) from multiple data points. The long-term climate information is input into the trained long-term hydrological cycle conceptual mechanism model to output the long-term water demand, thereby obtaining the predicted long-term water demand of the irrigation area under the background of climate change.

[0069] Since the calculated theoretical water demand (short-term and long-term water demand) does not consider factors such as irrigation system and canal losses in the irrigation area, but the actual water pumping volume in the irrigation area is based to some extent on the weather forecast for the next few days, although there is a certain difference between the theoretical water demand and the actual water pumping volume in the irrigation area, the meteorological factors and theoretical water demand in the next few days have strong reference value for predicting the actual water pumping volume in the irrigation area. Therefore, this invention uses historical short-term climate information as input and predicted historical daily crop water demand as output. It uses a generalized regression neural network (RBF) machine learning intelligent algorithm to correct the calculated short-term hydrological cycle conceptual mechanism model, thus obtaining a trained short-term hydrological cycle conceptual mechanism model.

[0070] In practical applications, the specific operations are as follows:

[0071] Based on future weather forecasts, short-term weather forecast data for the target irrigation area was obtained, which previously included:

[0072] Obtain crop planting data; crop planting data includes historical actual daily irrigation water volume in the irrigation area and historical short-term weather forecast data.

[0073] Historical short-term weather forecast data are used to obtain historical short-term climate information.

[0074] By inputting historical short-term climate information into a short-term hydrological cycle conceptual mechanism model, the historical daily crop water demand can be predicted.

[0075] The error in daily water demand is obtained by comparing the predicted daily crop water demand with the actual daily irrigation water demand in the irrigation area.

[0076] The short-term hydrological cycle conceptual mechanism model is trained based on the daily water demand error to obtain the trained short-term hydrological cycle conceptual mechanism model.

[0077] The above describes the training process of the short-term hydrological cycle conceptual mechanism model. The specific training process of the long-term hydrological cycle conceptual mechanism model is the same as that of the short-term hydrological cycle conceptual mechanism model, except that the input data is replaced with historical long-term weather forecast data.

[0078] In practice, short-term climate information should include at least: reference evapotranspiration and daily precipitation absorption.

[0079] The reference evaporation rate is calculated using the following formula:

[0080]

[0081] Among them, ET 0r For reference evaporation rate; R nr The historical average daily net solar radiation (MJ·m) -2 ·d -1 G r Historical daily average soil heat flux (MJ·m) -2 ·d -1 ;Δ r The average slope of the historical daily saturated vapor pressure-temperature curve (kg·Pa·℃) -1 ;γ r The hygrometer constant is kg·Pa·℃ -1 ;u 2r The average wind speed at a height of 2m on historical days (m·s) -1 ;e sr The average daily saturated vapor pressure in historical data (kPa); e ar The average historical daily water vapor pressure (kPa); T r The historical average temperature at a height of 2m is ℃.

[0082] The formula for daily precipitation absorption is:

[0083]

[0084] Where P0 is the daily precipitation absorption, P r The historical daily average precipitation in mm, i mr This represents the historical maximum soil infiltration rate in mm.

[0085] Long-term climate information should include at least: monthly average crop evapotranspiration and monthly average precipitation absorption during the growing season.

[0086] The formula for the average monthly crop evapotranspiration during the growing season is:

[0087]

[0088] Among them, ET 0y R is the average monthly crop evapotranspiration during the growing season. ny The average monthly net solar radiation of that year (MJ·m) -2 ·d -1 G y The average monthly soil heat flux (MJ·m) for that year -2 ·d -1 ;Δ y The average slope of the monthly saturated water vapor pressure-temperature curve (kg·Pa·℃) -1 ;γ y The hygrometer constant is kg·Pa·℃ -1 ;u 2y The average wind speed at a height of 2m in that month (m·s) -1 ;e sy The average monthly saturated vapor pressure (kPa) for that year; e ay The average value of the actual monthly water vapor pressure in that year (kPa); T y The average temperature at a height of 2m in that month was ℃.

[0089] The formula for the average monthly precipitation absorption during the growing season is:

[0090]

[0091] Where P1 is the average monthly precipitation absorption during the growing season, P y i represents the average monthly precipitation in mm for that year. my The maximum soil infiltration rate in that year is measured in mm.

[0092] Example 2

[0093] This invention provides an irrigation area water demand prediction system based on long-term and short-term meteorological data. The irrigation area water demand prediction system based on long-term and short-term meteorological data is applied to the method in Embodiment 1. The irrigation area water demand prediction system based on long-term and short-term meteorological data includes:

[0094] The model building module is used to construct short-term and long-term hydrological cycle conceptual mechanism models.

[0095] The short-term climate information acquisition module is used to obtain future short-term weather forecast data for the target irrigation area based on future weather forecasts; and to obtain short-term climate information based on the future short-term weather forecast data.

[0096] The short-term water demand determination module is used to input short-term climate information into the trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area.

[0097] The long-term climate information acquisition module is used to select 12 CMIP6 datasets applicable to the target irrigation area and obtain monthly-scale future meteorological data averaged from multiple datasets; long-term climate information is obtained based on the monthly-scale future meteorological data.

[0098] The long-term water demand determination module is used to input long-term climate information into the trained long-term hydrological cycle conceptual mechanism model to obtain the long-term water demand of the target irrigation area.

[0099] In practice, the system also includes a model training module.

[0100] The model training module specifically includes: a crop planting data acquisition module, a module for determining historical daily crop water requirements, a module for determining daily water requirements error, and a module for determining the short-term hydrological cycle conceptual mechanism model after training.

[0101] The crop planting data acquisition module is used to acquire crop planting data. This crop planting data includes: historical actual daily irrigation water volume in the irrigation area and historical short-term weather forecast data.

[0102] The historical short-term climate information determination module is used to obtain historical short-term climate information based on historical short-term weather forecast data.

[0103] The module for predicting historical daily crop water requirements is used to input historical short-term climate information into the short-term hydrological cycle conceptual mechanism model to obtain the first predicted historical daily crop water requirements.

[0104] The daily water demand error determination module is used to obtain the first daily water demand error based on the first predicted historical daily crop water demand and the historical actual daily irrigation water volume of the irrigation area.

[0105] The module for determining the short-term hydrological cycle conceptual mechanism model after training is used to train the short-term hydrological cycle conceptual mechanism model based on the water demand error on the first day, so as to obtain the trained short-term hydrological cycle conceptual mechanism model.

[0106] In one embodiment, the present invention also provides a computer-readable storage medium storing a computer program that, when executed, implements the method as described in Embodiment 1.

[0107] In one embodiment, the present invention also 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 computer program to implement the method as described in Embodiment 1.

[0108] The advantage of this invention is that it enables short-term and long-term prediction of water demand in irrigation districts even in the absence of a proper irrigation system. The water demand prediction, which combines short-term and long-term meteorological data, provides a reference for irrigation district staff to plan short-term water resource allocation in advance, while the long-term water demand prediction can provide a reference for the planning of water conservancy facilities such as pumping and drainage systems in the irrigation district.

[0109] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0110] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting water requirement in an irrigation area based on long-term and short-term weather data, characterized by, The irrigation district water demand prediction method based on long-term and short-term meteorological data includes: Construct a conceptual mechanism model for the short-term hydrological cycle and a conceptual mechanism model for the long-term hydrological cycle; Obtain short-term weather forecast data for the target irrigation area based on future weather forecasts; Short-term climate information is obtained based on the aforementioned future short-term weather forecast data; The short-term climate information is input into the trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area. Twelve CMIP6 datasets applicable to the target irrigation area were selected to obtain average monthly future meteorological data from multiple datasets; Long-term climate information is obtained based on the monthly-scale future meteorological data; The long-term climate information is input into the trained long-term hydrological cycle conceptual mechanism model to obtain the long-term water demand of the target irrigation area. The short-term climate information includes at least: reference evapotranspiration and daily precipitation absorption; the reference evapotranspiration is calculated as follows: ； in, For reference evaporation rate; The average daily net solar radiation is MJ·m⁻²·d⁻¹. The historical daily average soil heat flux is MJ·m⁻²·d⁻¹. The average slope of the historical daily saturated vapor pressure-temperature curve is 1 kg·Pa·℃. The constant of the hygrometer is kg·Pa·℃⁻¹; The average wind speed at a height of 2m on historical days (m·s⁻¹). The average daily saturated water vapor pressure in historical data (kPa); The average value of the actual water vapor pressure on historical days (kPa); The historical average temperature at a height of 2m is ℃; The formula for the daily precipitation absorption is: ； wherein, is the daily amount of precipitation, is the historical daily average precipitation in mm, is the historical maximum soil infiltration in mm; The long-term climate information includes at least: monthly average crop evapotranspiration during the growing season and monthly average precipitation absorption during the growing season; the monthly average crop evapotranspiration during the growing season is calculated using the following formula: ； in, This represents the average monthly crop evapotranspiration during the growing season. The average value of the net solar radiation for that month is MJ·m⁻²·d⁻¹. The average monthly soil heat flux (MJ·m⁻²·d⁻¹) for that year; It represents the average slope of the monthly saturated water vapor pressure-temperature curve in kg·Pa·℃⁻¹. The constant of the hygrometer is kg·Pa·℃⁻¹; The average wind speed at a height of 2m in that year and month is 1 m·s⁻¹. The average monthly saturated water vapor pressure for that year is expressed in kPa. The average value of the actual water vapor pressure for that month in that year, expressed in kPa. The average temperature at a height of 2m in that month was °C. The formula for the average monthly precipitation absorption during the growing season is: ； in, This represents the average monthly rainfall absorption during the growing season. The average monthly precipitation for that year (in mm). The maximum soil infiltration rate in that year is measured in mm.

2. The long short-term weather data based irrigation demand forecasting method according to claim 1, characterized in that, The process of obtaining short-term weather forecast data for the target irrigation area based on future weather forecasts also includes: Obtain crop planting data; the crop planting data includes: historical actual daily irrigation water volume in the irrigation area and historical short-term weather forecast data; Based on the aforementioned historical short-term weather forecast data, historical short-term climate information is obtained; The historical short-term climate information is input into the short-term hydrological cycle conceptual mechanism model to obtain the predicted historical daily crop water demand; The daily water demand error is obtained by comparing the predicted historical daily crop water demand with the historical actual daily irrigation water volume in the irrigation area. The short-term hydrological cycle conceptual mechanism model is trained based on the daily water demand error to obtain the trained short-term hydrological cycle conceptual mechanism model.

3. A system for predicting water requirement in an irrigation area based on long-term and short-term weather data, characterized in that, The irrigation area water demand prediction system based on long-term and short-term meteorological data is applied to any one of claims 1-2, and the irrigation area water demand prediction system based on long-term and short-term meteorological data includes: The model building module is used to build short-term and long-term hydrological cycle conceptual mechanism models. The short-term climate information acquisition module is used to obtain future short-term weather forecast data for the target irrigation area based on future weather forecasts; and to obtain short-term climate information based on the future short-term weather forecast data. The short-term water demand determination module is used to input the short-term climate information into the trained short-term hydrological cycle conceptual mechanism model to obtain the short-term water demand of the target irrigation area. The long-term climate information acquisition module is used to select 12 CMIP6 datasets applicable to the target irrigation area, obtain monthly-scale future meteorological data averaged across multiple datasets, and obtain long-term climate information based on the monthly-scale future meteorological data. The long-term water demand determination module is used to input the long-term climate information into the trained long-term hydrological cycle conceptual mechanism model to obtain the long-term water demand of the target irrigation area.

4. The long short-term weather data based irrigation district water requirement prediction system of claim 3, wherein, The short-term climate information acquisition module previously also included: a model training module; The model training module specifically includes: The crop planting data acquisition module is used to acquire crop planting data; the crop planting data includes: historical actual daily irrigation water volume in the irrigation area and historical short-term weather forecast data; The historical short-term climate information determination module is used to obtain historical short-term climate information based on the historical short-term weather forecast data. The module for determining the historical daily crop water requirement is used to input the historical short-term climate information into the short-term hydrological cycle conceptual mechanism model to obtain the first predicted historical daily crop water requirement. The daily water demand error determination module is used to obtain the first daily water demand error based on the first predicted historical daily crop water demand and the historical actual daily irrigation water volume of the irrigation area. The module for determining the short-term hydrological cycle conceptual mechanism model after training is used to train the short-term hydrological cycle conceptual mechanism model based on the water demand error of the first day, so as to obtain the trained short-term hydrological cycle conceptual mechanism model.

5. A computer readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed, implements the method as described in any one of claims 1 to 2.

6. An electronic device, comprising: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 2.

Images