Irrigation area water resource demand information prediction method and device and storage medium

Through the preprocessing of initial meteorological indicator information and the application of deep learning models, the accuracy of water resource demand prediction in irrigation area is improved, the problem of low accuracy of water resource demand prediction in the existing technology is solved, and the waste of water supply scheduling resources is reduced .

CN119026730APending Publication Date: 2024-11-26ZHENGZHOU UNIV +4
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411026597.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing water resource demand prediction algorithm has low accuracy in the prediction of water resource demand information in irrigation areas, resulting in wasted water supply scheduling resources.

Method used

By obtaining the initial meteorological indicator information, preprocessing is performed to generate a set of meteorological indicator information, and inputting it into the pre-trained water resource demand prediction model, using deep learning to build a long-term and short-term memory neural network model and introducing an attention mechanism, it is more accurate irrigation area water resource demand forecast information to ensure accurate dispatch of water supply equipment.

Benefits of technology

It improves the accuracy of water resource demand forecast in irrigation areas, reduces the waste of dispatched resources, and ensures that accurate water resource demand is provided under preset water supply conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure BDA0004968722880000071
    Figure BDA0004968722880000071
  • Figure BDA0004968722880000081
    Figure BDA0004968722880000081
  • Figure HDA0004968722900000011
    Figure HDA0004968722900000011
Patent Text Reader

Abstract

The embodiment of the invention relates to the field of irrigation area water resource demand information prediction, in particular to an irrigation area water resource demand information prediction method and device and a storage medium. One specific embodiment of the method comprises the following steps: acquiring an initial meteorological index information set; preprocessing the initial meteorological index information set to generate a meteorological index information set; inputting the meteorological index information set into a pre-trained water resource demand prediction model to obtain irrigation area water resource demand prediction information; and in response to determining that the irrigation area water resource demand prediction information meets the preset irrigation area water supply condition, controlling associated water supply equipment to carry out water supply treatment. According to the embodiment, waste of scheduling resources can be reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of irrigation district water resource demand information prediction, and specifically to an irrigation district water resource demand information prediction method, device and storage medium. Background Art

[0002] Providing accurate water demand to irrigation areas can reduce water waste and improve water utilization efficiency. At present, the commonly used method for predicting water demand information is to use a water demand prediction algorithm based on meteorological indicator information to predict water demand information. Among them, the water demand prediction algorithm can be regression analysis, time series analysis, and decay index method.

[0003] However, in practice, it is found that when the above method is used to predict the water resource demand information of the irrigation area, the following technical problems often occur:

[0004] The accuracy of water resource demand predicted by the water resource demand prediction algorithm is low. When the predicted water resource demand is low, it is necessary to repeatedly dispatch water supply equipment to supply water to the irrigation area, resulting in a waste of dispatching resources. Summary of the invention

[0005] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present application propose an irrigation area water resource demand information prediction method, a computer device, and a computer-readable storage medium to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present application provide a method for predicting water resource demand information for an irrigation area, the method comprising: obtaining an initial meteorological indicator information set; preprocessing the initial meteorological indicator information set to generate a meteorological indicator information set; inputting the meteorological indicator information set into a pre-trained water resource demand prediction model to obtain irrigation area water resource demand prediction information; in response to determining that the irrigation area water resource demand prediction information meets a preset irrigation area water supply condition, controlling associated water supply equipment to perform water supply processing.

[0008] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method described in any implementation of the first aspect is implemented.

[0009] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0010] The above-mentioned various embodiments of the present application have the following beneficial effects: through the irrigation area water resource demand information prediction method of some embodiments of the present application, the waste of scheduling resources can be reduced. Specifically, the reason for wasting scheduling resources is that the water resource demand predicted by the water resource demand prediction algorithm is low in accuracy. When the predicted water resource demand is low, it is necessary to repeatedly schedule the water supply equipment to supply water to the irrigation area. Based on this, the irrigation area water resource demand information prediction method of some embodiments of the present application. First, an initial meteorological indicator information set is obtained. Secondly, the above-mentioned initial meteorological indicator information set is preprocessed to generate a meteorological indicator information set. Thus, the missing values ​​in the meteorological indicator information can be identified and processed through preprocessing, and the integrity and accuracy of the meteorological indicator information can be ensured. Then, the above-mentioned meteorological indicator information set is input into the pre-trained water resource demand prediction model to obtain the irrigation area water resource demand prediction information. Therefore, by introducing deep learning into the irrigation area water resource demand prediction field, constructing a long short-term memory neural network model and introducing an attention mechanism, more accurate irrigation area water resource demand prediction information can be obtained. Finally, in response to determining that the above-mentioned irrigation area water resource demand prediction information meets the preset irrigation area water supply condition, the associated water supply equipment is controlled to perform water supply processing. In this way, under the preset irrigation area water supply conditions, through relatively accurate irrigation area water resource demand forecast information, water supply equipment can be dispatched to provide the irrigation area with relatively accurate water resource demand, which can reduce the waste of dispatching resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0012] Figure 1 is a flow chart of some embodiments of the irrigation area water resource demand information prediction method according to the present application;

[0013] Figure 2 It is a schematic diagram of the structure of a computer device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0014] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0020] Figure 1 The flowchart 100 of some embodiments of the irrigation area water resource demand information prediction method according to the present application is shown. The irrigation area water resource demand information prediction method comprises the following steps:

[0021] Step 101, obtaining an initial meteorological indicator information set.

[0022] In some embodiments, the execution subject (e.g., computing device) of the irrigation area water resource demand information prediction method can obtain the initial meteorological index information set of the irrigation area through a wired connection or a wireless connection. The initial meteorological index information in the initial meteorological index information set can represent but is not limited to: temperature, rainfall, sunshine time, air humidity, CO2 concentration, wind force, and air pressure. For example, the irrigation area can be an agricultural irrigation area, an urban water supply irrigation area, or an ecological protection irrigation area.

[0023] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0024] Step 102: pre-process the above-mentioned initial meteorological indicator information set to generate a meteorological indicator information set.

[0025] In some embodiments, the execution entity may pre-process the initial meteorological indicator information set to generate a meteorological indicator information set.

[0026] In practice, the execution subject may pre-process the initial meteorological indicator information set to generate a meteorological indicator information set by the following steps:

[0027] The first step is to perform data cleaning on the above-mentioned initial meteorological indicator information set to generate a meteorological indicator cleaned information set. In practice, the above-mentioned execution subject can perform missing value processing on each meteorological indicator information in the above-mentioned initial meteorological indicator information set in response to determining that the meteorological indicator information meets the preset missing condition, and generate meteorological indicator cleaned information by using a preset missing value algorithm to obtain a meteorological indicator cleaned information set. Among them, the preset missing condition can be that the meteorological indicator information representation is empty. For example, the preset missing value algorithm can be an interpolation method.

[0028] The second step is to perform feature selection processing on the meteorological indicator cleansing information set to generate a meteorological indicator feature information set. In practice, the execution subject may perform feature selection processing on the meteorological indicator cleansing information set by using a preset feature selection algorithm to generate a meteorological indicator cleansing information set. For example, the preset feature selection algorithm may be an embedding method.

[0029] The third step is to perform standardization processing on the above-mentioned meteorological indicator characteristic information set to generate a meteorological indicator information set. In practice, the above-mentioned execution subject can perform standardization processing on each meteorological indicator characteristic information in the meteorological indicator characteristic information set by using a preset standardization algorithm to generate meteorological indicator information and obtain a meteorological indicator information set. For example, the preset standardization algorithm can be a standard score method.

[0030] Step 103: input the above-mentioned meteorological indicator information set into a pre-trained water resource demand prediction model to obtain irrigation area water resource demand prediction information.

[0031] In some embodiments, the above-mentioned execution subject may input the above-mentioned meteorological indicator information set into a pre-trained water resource demand prediction model to obtain irrigation area water resource demand prediction information. The pre-trained water resource demand prediction model may be a pre-trained neural network model that takes the meteorological indicator information set as input and the irrigation area water resource demand information as output. The irrigation area water resource demand prediction information may represent the water resource demand required by the current irrigation area.

[0032] Optionally, the pre-trained water resource demand prediction model is trained through the following steps:

[0033] The first step is to obtain the initial training sample set.

[0034] In some embodiments, the execution subject may obtain the initial training sample set by wired connection or wireless connection. The initial training samples in the initial training sample set may include: an initial sample meteorological indicator information set and an initial sample irrigation area water resource demand forecast information. For example, the number of initial training samples in the initial training sample set may be 275.

[0035] In the second step, feature extraction is performed on each initial training sample in the initial training sample set to generate a training sample and obtain a training sample set.

[0036] In some embodiments, the execution subject may perform feature extraction processing on each initial training sample in the initial training sample set to generate training samples and obtain a training sample set. The training samples in the training sample set may include: a sample meteorological indicator information set and a sample irrigation area water resource demand forecast information.

[0037] In practice, the execution subject may perform feature extraction processing on each initial training sample in the initial training sample set to generate a training sample and obtain a training sample set by the following steps:

[0038] The first sub-step is to perform a multivariate regression analysis on the initial training samples to generate a meteorological index influencing index value set. In practice, the execution subject may perform a multivariate regression analysis on the initial training samples to generate a meteorological index influencing index value set through the following multivariate regression analysis steps:

[0039] The first multivariate regression analysis step, based on the initial training sample, performs the following screening steps:

[0040] The first screening step is to construct a multivariate meteorological index impact information regression model based on the initial training samples. The multivariate meteorological index impact information regression model is constructed based on the initial training samples by using a preset regression algorithm. For example, the multivariate meteorological index impact information regression model may be a multivariate linear regression model. The preset regression algorithm may be a multivariate regression algorithm.

[0041] In the second screening step, based on the multivariate meteorological indicator impact information regression model, correlation analysis is performed on each meteorological indicator impact information in the meteorological indicator impact information set included in the initial training sample and the water resource demand included in the initial training sample to generate a meteorological indicator significance value and obtain a meteorological indicator significance value set.

[0042] In practice, the execution subject may perform single sample inspection on each meteorological indicator impact information and water resource demand in the initial training sample in the meteorological indicator impact information set by using a preset single sample inspection algorithm to generate a meteorological indicator significance value and obtain a meteorological indicator significance value set. For example, the preset single sample inspection algorithm may be a variance analysis algorithm or a variance inspection algorithm.

[0043] In the third screening step, the meteorological indicator significance value with the largest meteorological indicator significance value set is determined as the meteorological indicator significance maximum value.

[0044] In the fourth screening step, the meteorological indicator significance value set from which the maximum meteorological indicator significance value is removed is determined as the target meteorological indicator significance value set.

[0045] In a fifth screening step, in response to determining that the target meteorological indicator significance value set meets a preset meteorological indicator condition, the target meteorological indicator significance value set is determined as a meteorological indicator influence indicator value set. The preset meteorological indicator condition may be that the number of target meteorological indicator significance values ​​in the target meteorological indicator significance value set is less than or equal to a preset significance value. For example, the preset significance value may be 5.

[0046] Optionally, in response to the meteorological indicator significance value set not satisfying the preset meteorological indicator condition, the initial training sample from which the meteorological indicator impact information corresponding to the maximum meteorological indicator significance value is removed is determined as the initial training sample for performing the above screening step again.

[0047] The second sub-step is to perform data normalization processing on the above-mentioned meteorological index impact index value set to generate a meteorological normalized index value set.

[0048] In practice, the above-mentioned execution entity can perform data normalization processing on the above-mentioned meteorological index impact index value set through the following formula to generate a meteorological normalized index value set:

[0049]

[0050] Among them, y i represents the ith meteorological normalized index value in the meteorological normalized index value set. i It represents the ith meteorological index influencing index value in the meteorological index influencing index value set. N represents the number of meteorological index influencing index values ​​in the meteorological index influencing index value set. i represents the sequence number.

[0051] The third sub-step is to fuse the above-mentioned meteorological normalized index value set and the above-mentioned initial training samples to generate training samples.

[0052] The third step is to select training samples from the training sample set.

[0053] In some embodiments, the execution entity may select training samples from a training sample set. In practice, the execution entity may randomly select training samples from a training sample set.

[0054] The fourth step is to input the sample meteorological index information set included in the selected training samples into the initial water resource demand prediction model to obtain the initial sample irrigation area water resource demand prediction information;

[0055] In some embodiments, the above-mentioned execution entity may input the sample meteorological indicator information set included in the selected training samples into the initial water resource demand prediction model to obtain the initial sample irrigation area water resource demand prediction information.

[0056] Among them, the initial water resource demand forecasting model can include the following four layers:

[0057] The first layer, the input layer, is used to input the sample meteorological indicator information set into the second layer.

[0058] The second layer, the processing layer, includes a first sub-model. The first sub-model can be a neural network model that takes a sample meteorological indicator information set as input and a first prediction information sequence as output. For example, the first sub-model can be a two-layer long short-term memory artificial neural network (Long-Short-Term-Memory) model.

[0059] The third layer, the self-attention layer, includes a second sub-model. The second sub-model may be a neural network model that takes the first prediction information sequence as input and the second prediction information sequence as output. For example, the second sub-model may be a self-attention mechanism (Self-Attention) model.

[0060] The fourth layer, the output layer, is used to: use the first second prediction information in the second prediction information sequence as the output of the entire initial water resource demand prediction model.

[0061] The fifth step is to determine the first difference value and the second difference value between the initial sample irrigation area water resource demand forecast information and the sample irrigation area water resource demand forecast information included in the selected training sample based on a preset loss function.

[0062] In some embodiments, based on a preset loss function, the execution subject may determine a first difference value and a second difference value between the initial sample irrigation area water resource demand forecast information and the sample irrigation area water resource demand forecast information included in the selected training sample. The loss function may be the following formula:

[0063]

[0064] Wherein, n represents the number of first prediction information in the first prediction information sequence. represents the i-th second prediction information in the second prediction information sequence. i represents the sample irrigation area water resource demand forecast information included in the training sample. RMS represents the first difference value. 2 Represents the second difference value. Represents the mean value of the water resource demand forecast information of the sample irrigation areas included in the training samples.

[0065] Optionally, in response to determining that the first difference value and the second difference value do not satisfy the above-mentioned preset difference condition, the initial water resource demand prediction model is determined as the trained water resource demand prediction model.

[0066] In a sixth step, in response to determining that the first difference value and the second difference value satisfy a preset difference condition, the network parameters of the initial water resource demand prediction model are adjusted.

[0067] In some embodiments, in response to determining that the first difference value and the second difference value meet a preset difference condition, the execution subject may adjust the network parameters of the initial water resource demand prediction model. The preset difference condition may be that the first difference value is less than the first preset difference value, and the second difference value is greater than the second preset difference value. For example, the first difference value may be 0.1. The second difference value may be 0.8.

[0068] In some embodiments, in response to determining that the first difference value and the second difference value do not satisfy the preset difference condition, the execution entity may determine the initial water resource demand prediction model as the trained water resource demand prediction model.

[0069] Step 104, in response to determining that the irrigation area water resource demand forecast information meets the preset irrigation area water supply conditions, controlling the associated water supply equipment to perform water supply processing.

[0070] In some embodiments, the execution subject may control the associated water supply equipment to perform water supply processing in response to determining that the irrigation area water resource demand forecast information meets the preset irrigation area water supply condition. The preset irrigation area water supply condition may be: the value represented by the irrigation area water resource demand forecast information is greater than or equal to the target irrigation area water resource amount. The associated water supply equipment may be a water supply equipment that is communicatively connected to the execution subject. The water supply equipment may be used to automatically adjust and control the water flow. For example, the target irrigation area water resource amount may be 108 cubic meters of water. The water supply equipment may refer to a sluice gate or a water pump.

[0071] The above-mentioned various embodiments of the present application have the following beneficial effects: through the irrigation area water resource demand information prediction method of some embodiments of the present application, the waste of scheduling resources can be reduced. Specifically, the reason for wasting scheduling resources is that the water resource demand predicted by the water resource demand prediction algorithm is low in accuracy. When the predicted water resource demand is low, it is necessary to repeatedly schedule the water supply equipment to supply water to the irrigation area. Based on this, the irrigation area water resource demand information prediction method of some embodiments of the present application. First, an initial meteorological indicator information set is obtained. Secondly, the above-mentioned initial meteorological indicator information set is preprocessed to generate a meteorological indicator information set. Thus, the missing values ​​in the meteorological indicator information can be identified and processed through preprocessing, and the integrity and accuracy of the meteorological indicator information can be ensured. Then, the above-mentioned meteorological indicator information set is input into the pre-trained water resource demand prediction model to obtain the irrigation area water resource demand prediction information. Therefore, by introducing deep learning into the irrigation area water resource demand prediction field, constructing a long short-term memory neural network model and introducing an attention mechanism, more accurate irrigation area water resource demand prediction information can be obtained. Finally, in response to determining that the above-mentioned irrigation area water resource demand prediction information meets the preset irrigation area water supply condition, the associated water supply equipment is controlled to perform water supply processing. In this way, under the preset irrigation area water supply conditions, through relatively accurate irrigation area water resource demand forecast information, water supply equipment can be dispatched to provide the irrigation area with relatively accurate water resource demand, which can reduce the waste of dispatching resources.

[0072] The present application also provides a computer device 200. Figure 2 As shown, the computer device 200 includes: a bus 201, a processor 202, a memory 203 and a communication interface 204. The processor 202, the memory 203 and the communication interface 204 communicate with each other through the bus 202. The computer device 200 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 200.

[0073] The bus 202 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The bus 202 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 202 may include a path for transmitting information between various components of the computer device 200 (for example, the memory 202, the processor 203, and the communication interface 204).

[0074] The processor 203 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0075] The memory 202 may include a volatile memory, such as a random access memory (RAM). The memory 202 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0076] The memory 202 stores executable program codes, and the processor 202 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module, sampling module, determination module, and mixing module, thereby implementing the aforementioned irrigation area water resource demand information prediction method. That is, the memory 202 stores instructions for executing the aforementioned irrigation area water resource demand information prediction method.

[0077] The communication interface 204 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 200 and other devices or a communication network.

[0078] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads instructions stored in a memory through the data interface to execute the above-mentioned irrigation area water resource demand information prediction method.

[0079] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the irrigation area water resource demand information prediction method.

[0080] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting water resource demand information in an irrigation area, comprising: Obtaining an initial set of meteorological indicator information; Preprocessing the initial meteorological indicator information set to generate a meteorological indicator information set; Inputting the meteorological indicator information set into a pre-trained water resource demand forecasting model to obtain irrigation area water resource demand forecasting information; In response to determining that the irrigation area water resource demand forecast information meets the preset irrigation area water supply conditions, the associated water supply equipment is controlled to perform water supply processing.

2. The irrigation area water resource demand information prediction method according to claim 1, wherein: The preprocessing of the initial meteorological indicator information set to generate a meteorological indicator information set includes: Performing data cleaning processing on the initial meteorological indicator information set to generate a meteorological indicator cleansing information set; Performing feature selection processing on the meteorological indicator cleaning information set to generate a meteorological indicator feature information set; The meteorological indicator feature set is standardized to generate a meteorological indicator information set.

3. The irrigation area water resource demand information prediction method according to claim 1, wherein: The pre-trained water resource demand prediction model is trained in the following way: Obtain an initial training sample set; Performing feature extraction processing on each initial training sample in the initial training sample set to generate a training sample, thereby obtaining a training sample set, wherein the training samples in the training sample set include: a sample meteorological index information set and sample irrigation area water resource demand forecast information; Select training samples from the training sample set; Inputting the sample meteorological index information set included in the selected training samples into the initial water resource demand prediction model to obtain the initial sample irrigation area water resource demand prediction information; Based on a preset loss function, determining a first difference value and a second difference value between the initial sample irrigation area water resource demand prediction information and the sample irrigation area water resource demand prediction information included in the selected training sample; In response to determining that the first difference value and the second difference value satisfy a preset difference condition, a network parameter of the initial water resource demand prediction model is adjusted.

4. The irrigation area water resource demand information prediction method according to claim 3, wherein: The method further comprises: In response to determining that the first difference value and the second difference value do not satisfy the preset difference condition, the initial water resource demand prediction model is determined as the trained water resource demand prediction model.

5. The irrigation area water resource demand information prediction method according to claim 3, wherein: The step of performing feature extraction processing on each initial training sample in the initial training sample set to generate a training sample includes: Performing multivariate regression analysis on the initial training samples to generate a meteorological index influencing index value set; Performing data normalization processing on the meteorological index impact index value set to generate a meteorological normalized index value set; The meteorological normalized index value set and the initial training samples are fused to generate training samples.

6. The irrigation area water resource demand information prediction method according to claim 5, wherein: The initial training samples in the initial training sample set include: a meteorological index impact information set and water resource demand; and the multiple regression analysis processing of the initial training samples to generate a meteorological index impact index value set includes: Based on the initial training samples, the following screening steps are performed: Based on the initial training samples, a regression model of the impact information of multiple meteorological indicators is constructed; Based on the multivariate meteorological index impact information regression model, the correlation analysis is performed on each meteorological index impact information in the meteorological index impact information set included in the initial training sample and the water resource demand included in the initial training sample to generate a meteorological index significance value and obtain a meteorological index significance value set; The meteorological indicator significance value with the largest meteorological indicator significance value set is determined as the meteorological indicator significance maximum value; The meteorological index significance value set from which the maximum value of the meteorological index significance is removed is determined as the target meteorological index significance value set; In response to determining that the target meteorological indicator significance value set meets the preset meteorological indicator condition, the target meteorological indicator significance value set is determined as the meteorological indicator influence indicator value set.

7. The irrigation area water resource demand information prediction method according to claim 6, wherein: The method further comprises: In response to the meteorological indicator significance value set not satisfying the preset meteorological indicator condition, the initial training sample from which the meteorological indicator impact information corresponding to the maximum meteorological indicator significance value is removed is determined as the initial training sample for performing the screening step again.

8. A computer device, wherein: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.