A method, apparatus, medium, and equipment for constructing variable irrigation prescription maps

Abstract

This invention provides a method, apparatus, medium, and equipment for constructing a variable irrigation prescription map, comprising: acquiring UAV image data, IoT soil sensor data, and meteorological forecast precipitation data in the same time and space image coordinate system; calculating the normalized vegetation index and land surface temperature from the image data, and calculating the vegetation fractal cover based on the normalized vegetation index; establishing a temperature-fractal cover feature space based on land surface temperature and vegetation fractal cover, and calculating the temperature-vegetation drought index; establishing a functional relationship between soil moisture content and temperature-drought vegetation index using IoT soil moisture content data and temperature-drought vegetation index data as input, and estimating the soil moisture content of the entire region; extracting the field water holding capacity during the current crop planting period; calculating the irrigation quota using the field water holding capacity, the soil moisture content of the entire region, and meteorological forecast precipitation data, and obtaining the final variable irrigation prescription map by combining agronomic and irrigation cycle data.

Description

Technical Field

[0001] This invention belongs to the field of crop irrigation technology, and particularly relates to a method, apparatus, medium and equipment for constructing variable irrigation prescription maps. Background Technology

[0002] Existing variable irrigation technologies calculate irrigation prescriptions based on field evapotranspiration. Application CN202110078410.8 discloses a method that calculates field evapotranspiration using meteorological and crop growth data, retrieves field soil moisture from crop information extracted via remote sensing multispectral data and soil data, and calculates an irrigation prescription map based on evapotranspiration and soil moisture data. The upper limit of irrigation is set at field capacity, and the number of irrigations and irrigation volume are estimated by combining the irrigation cycle and field evapotranspiration. Application CN202310335560.1 discloses a method that uses meteorological data to obtain evapotranspiration, and simultaneously obtains soil moisture content and the lower limit of moisture content requirements from field measurements. Irrigation volume is then calculated based on evapotranspiration and forecasted precipitation data. Application CN202110078410.8 proposes a method for inverting irrigation prescription maps based on UAV spectral data. The specific implementation process is as follows: 1) Collect remote sensing multispectral data; 2) Extract crop canopy information and crop water deficit index from remote sensing images; 3) Calculate field evapotranspiration based on the energy balance principle and field canopy radiation temperature; 4) Conduct field sampling during the daily synchronization interval of UAV image acquisition data to obtain soil moisture content and field water holding capacity; 5) Obtain variable irrigation prescriptions based on the principle that the irrigation upper limit reaches the soil field water holding capacity, combined with irrigation cycle and meteorological precipitation data.

[0003] However, existing technologies have the following drawbacks: ① In calculating variable irrigation prescriptions, field evapotranspiration is calculated using the Penman formula as the water requirement for a single irrigation of crops. In the single-crop coefficient method, the Penman formula involves numerous physical parameters, including air temperature, wind speed, water vapor pressure, humidity, net radiation, crop height, and albedo, making the calculation of field evapotranspiration extremely complex. The soil transpiration coefficient is particularly difficult to determine accurately. Calculating field evapotranspiration is even more challenging in the dual-crop coefficient method. This drawback makes this process difficult to implement or widely apply. ② In generating variable irrigation prescriptions, soil moisture content needs to be measured, and field capacity needs to be extracted as the upper limit for irrigation. Existing technologies use field sampling and measurement methods, such as ring sampling or other methods, to obtain soil moisture content, which is time-consuming, labor-intensive, and prone to human error. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method, apparatus, medium, and equipment for constructing variable irrigation prescription maps, which can further simplify the irrigation prescription map inversion process and quickly guide variable irrigation operations without requiring extensive field observations.

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

[0006] The first aspect of the present invention provides a method for constructing a variable irrigation prescription map, comprising the following steps:

[0007] Acquire infrared, visible, and near-infrared band data from the same time, region, and reference coordinate system, as well as soil moisture content data and meteorological precipitation forecast data observed by IoT soil sensors.

[0008] Land surface temperature is extracted from infrared data, and normalized vegetation index is calculated from visible and near-infrared data. Vegetation fractal cover is calculated based on the normalized vegetation index. Based on the calculated land surface temperature and vegetation fractal cover, a temperature-fractal cover feature space is established, and vegetation dry edge equation and wet edge equation are obtained. Temperature vegetation drought index is calculated based on the dry and wet edge equation.

[0009] A functional response relationship was established between the temperature-vegetation drought index and the soil moisture content data observed by IoT soil sensors to obtain a mathematical function model. Based on the temperature-vegetation drought index data, the soil moisture content of the entire region was calculated.

[0010] Extract field water holding capacity during the current crop planting process;

[0011] The irrigation cycle and irrigation volume are determined by combining crop irrigation quota standards, soil moisture content of the whole region and meteorological forecast precipitation data. The maximum irrigation volume shall not exceed the upper limit of field water holding capacity. A single irrigation quota is generated. Irrigation zoning management is carried out based on the single irrigation quota, which is divided into different irrigation areas. The total irrigation water consumption in different irrigation areas is calculated by combining planting area data. A variable irrigation prescription map is obtained by combining planting area and irrigation cycle.

[0012] A second aspect of the present invention provides a variable irrigation prescription map construction apparatus, comprising:

[0013] The data acquisition module is used to acquire infrared, visible, and near-infrared band data captured by UAV multispectral cameras at the same time, in the same area, and in the same reference coordinate system, as well as soil moisture content data observed by IoT sensors.

[0014] The index calculation module is used to extract the surface temperature from infrared band data, calculate the normalized vegetation index from visible light band data and near-infrared band data, calculate the vegetation fractal coverage based on the normalized vegetation index, establish the temperature-fractal coverage feature space, obtain the vegetation dry edge equation and wet edge equation, calculate the temperature vegetation drought index based on the dry and wet edge equation, and classify the soil drought level.

[0015] The soil moisture content inversion module is used to establish a functional response relationship between temperature and vegetation drought index and soil moisture content data, obtain a mathematical function model, and calculate the soil moisture content of the entire region based on temperature and vegetation drought index data.

[0016] The field water holding capacity extraction module is used to obtain the process line of soil moisture content change in the field after sufficient rainfall, and the peak point data of the process line is taken as the field water holding capacity.

[0017] The variable prescription construction module is used to determine the irrigation cycle and irrigation volume by combining crop irrigation quota standards, soil moisture content and meteorological forecast precipitation data, generate a variable irrigation prescription map, and cluster the irrigation prescription map according to the K-means clustering method to divide the field management area into different irrigation plots. Combined with the planting area data, the total irrigation water in different irrigation plots is calculated to obtain the final variable irrigation prescription map.

[0018] A third aspect of the present invention provides a computer-readable storage medium.

[0019] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the variable irrigation prescription map construction method described above.

[0020] A fourth aspect of the present invention provides an electronic device.

[0021] 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 program to perform the steps described above in a variable irrigation prescription map construction method.

[0022] The present invention has the following beneficial effects:

[0023] This invention extracts surface temperature and normalized vegetation index (NDI) from infrared, visible, and near-infrared data captured by a UAV multispectral camera. The vegetation index is then converted into vegetation fractal cover, resulting in a temperature-vegetation fractal cover feature space. By calculating dry and wet edge equations, a temperature-vegetation drought index is obtained. Finally, soil moisture content data obtained from IoT sensors is fitted with the temperature-vegetation drought index using a random forest model to obtain the overall soil moisture content. The field capacity is then differentially calculated with the soil moisture content fitting results to obtain a variable irrigation prescription map. After k-means clustering of the variable irrigation prescription map, the field management area is divided into different irrigation plots. Combined with planting area data, the total irrigation water consumption within each irrigation plot is calculated.

[0024] This invention utilizes drone imagery data and ground-based IoT sensor data, coupling the two to avoid large-scale field sampling and solve the time-consuming and labor-intensive problem of existing variable irrigation prescription construction technologies. Addressing the complexity of calculating field evapotranspiration during irrigation quota acquisition, this invention proposes a differential calculation alternative method, avoiding the acquisition of numerous physical parameters and mathematical calculations, thus improving the efficiency of variable irrigation prescription construction. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating a method for constructing a variable irrigation prescription map according to an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of a variable irrigation prescription map construction device according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other. To achieve the above objectives, this invention adopts the following technical solution.

[0029] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0030] Figure 1 This is a schematic flowchart of a variable irrigation prescription map construction method according to an embodiment of the present invention. The method includes:

[0031] Acquire infrared, visible, and near-infrared band data, as well as soil moisture content data and meteorological forecast precipitation data, from the same time, region, and reference coordinate system.

[0032] The drone multispectral camera can use a multi-rotor drone equipped with a multispectral and thermal infrared camera (such as the M350RTK drone + AQ300 Pro camera) to capture infrared band data, visible light band data and near-infrared band data.

[0033] Soil moisture content data is collected using IoT soil sensors, specifically soil sensors (such as the OHR-MT40-0-L10 model).

[0034] Precipitation data for weather forecasts can be obtained from data from the local weather forecasting center.

[0035] Land surface temperature is extracted from infrared data, and normalized vegetation index is calculated from visible and near-infrared data. Vegetation fractal cover is calculated based on the normalized vegetation index. Based on the calculated land surface temperature and vegetation fractal cover, a temperature-fractal cover feature space is established, and vegetation dry edge equation and wet edge equation are obtained. Temperature-vegetation drought index is calculated based on the dry-wet edge equation, and soil drought level is classified.

[0036] In a specific embodiment, the normalized vegetation index (NDI) is calculated using near-infrared and visible light bands. Land surface temperature is calculated using a single-window algorithm and expressed in Kelvin.

[0037] ;

[0038] in, This is near-infrared band data. For visible light band data, The normalized vegetation index is the calculated value.

[0039] In other embodiments, vegetation index and surface temperature can also be calculated according to other preset rules.

[0040] In establishing the temperature-fractal cover feature space, vegetation fractal cover is calculated by normalizing vegetation indices.

[0041] ;

[0042] in, 、 These are its maximum and minimum values, respectively. The vegetation fractal coverage is calculated based on the vegetation index and is used to represent the growth status and lushness of crops.

[0043] The calculation process for the temperature drought vegetation index is as follows:

[0044] Geographic registration was performed on visible light and near-infrared data, and the normalized vegetation index and land surface temperature were calculated for each pixel of the image.

[0045] Calculate vegetation fractal coverage based on the calculated normalized vegetation index;

[0046] A temperature-fractal vegetation cover feature space is established. Temperature is represented by the ordinate, and vegetation fractal cover by the abscissa.

[0047] With a step size of 0.01, the dry edge equation and wet edge equation are obtained by fitting the temperature-fractal cover feature space, and the temperature drought vegetation index is calculated based on the dry and wet edge equations.

[0048] ;

[0049] ;

[0050] ;

[0051] in, and In the temperature-fractal coverage feature space, different The values ​​correspond to the maximum and minimum values, a and b are the fitting parameters for the dry edge equation, and c and d are the fitting parameters for the wet edge equation. It is the surface temperature value. It is the calculated temperature drought vegetation index.

[0052] For the IoT soil sensor data at each location, temperature, drought, and vegetation indices at the same location are used to form data pairs. With the temperature, drought, and vegetation indices as the independent variable and the soil moisture content data observed by the IoT soil sensors as the dependent variable, the soil moisture content of all pixels is obtained by fitting the data using the random forest method in machine learning.

[0053] It should be noted that existing techniques, such as the random forest method in machine learning, can be used when fitting the dry and wet edge equations based on the temperature-fractal coverage feature space, but these will not be elaborated here.

[0054] The random forest fitting method was used to establish a function response relationship between temperature, vegetation drought index and soil moisture content data of pixels, and a mathematical function model was obtained. Based on the temperature, vegetation drought index data, the soil moisture content of the whole region was calculated.

[0055] In a specific embodiment, the temperature drought vegetation index is used as the independent variable and soil moisture content data is used as the dependent variable to fit and estimate the soil moisture content of the whole region.

[0056] In other embodiments, the soil moisture content of the entire area can also be calculated according to other preset rules.

[0057] After sufficient rainfall or a single full irrigation, soil moisture content data is obtained by observing soil moisture content data through IoT soil sensors to obtain a process line of changes in field soil moisture content after sufficient rainfall, and the peak point data of the process line is taken as the field water holding capacity;

[0058] The irrigation cycle and irrigation volume are determined by combining crop irrigation quota standards, soil moisture content across the region, and meteorological forecast precipitation data. The maximum irrigation volume shall not exceed the upper limit of field capacity, thus generating a single irrigation quota.

[0059] ;

[0060] in, It is the water-filling quota for a single pixel. These are irrigation quota standards for different crops. It represents the soil moisture content of a single pixel. It is a single pixel of weather forecast precipitation data.

[0061] Irrigation is zoned and managed based on irrigation quotas, dividing the area into different irrigation zones. The total irrigation water consumption in each irrigation zone is calculated by combining planting area data and irrigation cycle data. A variable irrigation prescription map is then obtained by combining planting area and irrigation cycle data.

[0062] In a specific embodiment, K-means clustering is used for irrigation zone management.

[0063] In other embodiments, irrigation zoning management can also be performed according to other preset rules.

[0064] Figure 2 This is a schematic diagram of a variable irrigation prescription map construction device according to an embodiment of the present invention. This embodiment is similar to... Figure 1 Corresponding methods, such as Figure 2 As shown, a variable irrigation prescription map construction device in this embodiment may include:

[0065] The data acquisition module 201 is used to acquire infrared band data, visible light band data and near-infrared band data captured by UAV multispectral cameras at the same time, in the same area and in the same reference coordinate system, as well as soil moisture content data observed by IoT sensors.

[0066] The index calculation module 202 is used to extract the surface temperature from the infrared band data, calculate the normalized vegetation index from the visible light band data and the near-infrared band data, calculate the vegetation fractal coverage based on the normalized vegetation index, establish the temperature-fractal coverage feature space, obtain the vegetation dry edge equation and wet edge equation, calculate the temperature vegetation drought index based on the dry and wet edge equation, and classify the soil drought level.

[0067] Soil moisture content inversion module 203 is used to establish a functional response relationship between temperature and vegetation drought index and soil moisture content data, obtain a mathematical function model, and calculate the soil moisture content of the entire region based on temperature and vegetation drought index data.

[0068] The field water holding capacity extraction module 204 is used to obtain the process line of soil moisture content change in the field after sufficient rainfall, and the peak point data of the process line is taken as the field water holding capacity.

[0069] The variable prescription construction module 205 is used to determine the irrigation cycle and irrigation volume by combining crop irrigation quota standards, soil moisture content and meteorological forecast precipitation data, generate a variable irrigation prescription map, and cluster the irrigation prescription map according to the K-means clustering method to divide the field management area into different irrigation plots. Combined with the planting area data, the total irrigation water in different irrigation plots is calculated to obtain the final variable irrigation prescription map.

[0070] It should be noted here that, Figure 2 The variable irrigation prescription map construction device includes the data acquisition module 201, the index calculation module 202, the soil moisture content inversion module 203, the field water holding capacity module 204, and the variable irrigation prescription construction module 205. Figure 1 The specific implementation process of steps S101 to S105 in the variable irrigation prescription map construction method is the same, and will not be repeated here.

[0071] Reference Figure 3 A schematic diagram of an electronic device is provided. It should be noted that... Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0072] like Figure 3As shown, the electronic device includes a central processing unit 301, which can perform various appropriate actions and processes based on a program stored in a read-only memory 302 or a program loaded from a storage section 308 into a random access memory 303. The random access memory 303 also stores various programs and data required for system operation. The central processing unit 301, the read-only memory 302, and the random access memory 303 are interconnected via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0073] The following components are connected to the input / output interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a local area network (LAN) card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 310 as needed so that computer programs read from it can be installed into the storage section 308 as needed.

[0074] When the central processing unit 301 in the electronic device of this embodiment executes the program, it achieves the following: Figure 1 The steps in the method shown.

[0075] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit 301, it performs the various functions defined in the apparatus of this application.

[0076] in, Figure 1 The computer program instructions corresponding to the method shown may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate 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 the process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0078] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method of constructing a variable irrigation prescription map, characterized by, The method comprises the following steps: Obtaining infrared band data, visible light band data and near-infrared band data in the same time, the same region and the same reference coordinate system, and soil moisture data observed by an Internet of Things soil sensor and meteorological forecast precipitation data; Extracting the ground surface temperature from the infrared band data, and calculating the normalized vegetation index from the visible light band data and the near-infrared band data, and calculating the vegetation fractal coverage based on the normalized vegetation index; based on the calculated ground surface temperature and the vegetation fractal coverage, a temperature-fractal coverage characteristic space is established, and a dry edge equation and a wet edge equation are obtained, and a temperature vegetation drought index is calculated based on the dry and wet edge equations; A function response relationship is established between the temperature vegetation drought index and the soil moisture data observed by the Internet of Things soil sensor, and a mathematical function model is obtained, and the soil moisture of the whole region is calculated based on the temperature vegetation drought index data; Extracting the field water holding capacity in the current crop planting process; Combining the crop irrigation quota standard, the soil moisture of the whole region and the meteorological forecast precipitation data to determine the irrigation period and the irrigation amount, and the maximum irrigation amount does not exceed the upper limit of the field water holding capacity, to generate a one-time irrigation quota, and based on the one-time irrigation quota, irrigation zoning management is carried out, different irrigation zones are divided, combined with the planting area data, the total irrigation water amount in different irrigation zones is calculated, and combined with the planting area and the irrigation period, a variable irrigation prescription map is obtained; The normalized vegetation index is calculated by using the near-infrared band and the visible light band; ； wherein, is near-infrared band data, is visible light band data, is a calculated normalized difference vegetation index; The vegetation fractal coverage is calculated by normalizing the vegetation index: ； wherein, 、 are the maximum and minimum values, respectively; is the fractal coverage of vegetation. The calculation process of the temperature drought vegetation index is as follows: The visible light band data and the near-infrared band data are geographically registered, and the normalized vegetation index and the ground surface temperature are calculated for each pixel of the image; The vegetation fractal coverage is calculated based on the calculated normalized vegetation index; A temperature-fractal coverage characteristic space is established; wherein the temperature is the ordinate, and the vegetation fractal coverage is the abscissa; Taking 0.01 as the step, the dry edge equation and the wet edge equation are fitted based on the temperature-fractal coverage characteristic space, and the temperature drought vegetation index is calculated based on the dry and wet edge equations; ； ； ； in, and In the temperature-fractal coverage feature space, different The values ​​correspond to the maximum and minimum values, a and b are the fitting parameters for the dry edge equation, and c and d are the fitting parameters for the wet edge equation. It is the surface temperature value. It is the calculated temperature drought vegetation index.

2. The variable irrigation prescription map construction method of claim 1, wherein, The multi-spectral camera of the unmanned aerial vehicle adopts a multi-rotor unmanned aerial vehicle carrying a multi-spectral and thermal infrared camera to capture infrared band data, visible light band data and near-infrared band data.

3. The variable irrigation prescription map construction method of claim 1, wherein, The calculation process of the soil moisture of the whole region is as follows: For the Internet of Things soil sensor data at each point, the temperature drought vegetation index at the same point is taken to form a data pair, and the temperature drought vegetation index is taken as the independent variable, and the soil moisture data observed by the Internet of Things soil sensor is taken as the dependent variable, and the soil moisture of all pixel points, i.e. the whole region, is fitted by a random forest method in machine learning.

4. The variable irrigation prescription map construction method of claim 1, wherein, The extraction principle of the field water holding capacity is as follows: After a sufficient irrigation or rainfall, the peak process line of the soil moisture data observed by the Internet of Things sensor in the current crop period is taken as the field water holding capacity.

5. A variable irrigation prescription map building apparatus implementing the method of any one of claims 1-4, characterized by, It comprises: The data acquisition module acquires infrared band data, visible light band data and near-infrared band data in the same time, the same region and the same reference coordinate system, and soil moisture data observed by an Internet of Things soil sensor and meteorological forecast precipitation data; The index calculation module is used for extracting the ground temperature from the infrared band data, calculating the normalized vegetation index from the visible light band data and the near-infrared band data, and calculating the vegetation fractal coverage based on the normalized vegetation index; based on the calculated ground temperature and the vegetation fractal coverage, a temperature-fractal coverage characteristic space is established, and a vegetation drought index is obtained; and based on the dry and wet edge equations, a temperature vegetation drought index is calculated; The soil moisture inversion module is used for establishing a functional response relationship between the temperature vegetation drought index and the soil moisture data observed by the Internet of Things soil sensor, obtaining a mathematical function model, and calculating the soil moisture of all regions based on the temperature vegetation drought index data; The field water holding capacity extraction module is used for extracting the field water holding capacity in the current crop planting process; The variable irrigation prescription construction module is used for determining the irrigation period and the irrigation amount by combining the crop irrigation quota standard, the soil moisture of the whole region and the meteorological forecast precipitation data, the maximum irrigation amount does not exceed the upper limit of the field water holding capacity, a one-time irrigation quota is generated, irrigation zoning management is carried out based on the one-time irrigation quota, different irrigation plots are divided, the total irrigation water amount in different irrigation plots is calculated combined with the planting area data, and a variable irrigation prescription map is obtained combined with the planting area and the irrigation period.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the steps in the variable irrigation prescription map construction method of any one of claims 1-4.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the steps in the variable irrigation prescription map construction method of any one of claims 1-4.

Images