A method, device, equipment, medium and product for generating variable irrigation prescription maps based on the synergy of drones and satellite remote sensing

Abstract

The present application discloses a method, device, equipment, medium and product for generating a variable irrigation prescription map based on the synergy of unmanned aerial vehicle (UAV) and satellite remote sensing, and relates to the field of agricultural information monitoring and agricultural irrigation technology. The method comprises formulating an irrigation management strategy for a sprinkler cluster based on the critical water demand period of crops; constructing a soil moisture inversion model for different growth stages based on UAV remote sensing information, and predicting and inverting the soil moisture content for different growth stages based on the conversion equation between UAV remote sensing information and satellite remote sensing information; determining a spatial distribution map of soil moisture content within the irrigation area of the sprinkler cluster; determining a spatial distribution map of water deficit within the control area of a single sprinkler equipment based on the irrigation information, the soil moisture inversion model and the spatial distribution map of soil moisture content; and determining a variable irrigation prescription map within the control area of a single sprinkler equipment based on the irrigation management strategy and the water deficit spatial distribution map. The present application can achieve precise irrigation management.

Description

Technical Field

[0001] The present application relates to the fields of agricultural information monitoring and agricultural irrigation technology, and in particular to a method, device, equipment, medium and product for generating a variable irrigation prescription map based on the synergy of unmanned aerial vehicle (UAV) and satellite remote sensing. Background Art

[0002] As the scale of high-standard farmland construction in China continues to expand, the area of flat, concentrated and contiguous arable land of more than 10,000 mu continues to increase, providing basic conditions for the installation and utilization of multiple large and medium-sized sprinkler irrigation equipment. At the same time, managed irrigation services, as a new type of high-level agricultural service, provide the possibility for the continuous, stable and precise operation of sprinkler clusters.

[0003] Considering the characteristics of the short and heavy water-demand period of crops, in order to achieve fast and low-cost precise water management of sprinkler irrigation clusters and avoid the occurrence of yield reduction caused by untimely irrigation, it is urgently necessary to combine remote sensing information to accurately judge the spatial distribution characteristics of water deficit within the irrigation area of the sprinkler irrigation cluster, so as to generate the sprinkler cluster rotation system and the variable irrigation prescription map for each sprinkler irrigation plot.

[0004] Using drones to acquire remote sensing information is limited by their flight endurance and permitted flight altitude (no more than 120 meters). The flight area of a single drone multispectral system is limited to approximately 2,775 mu (approximately 2,775 mu) during the permitted flight period (11:00 AM to 4:00 PM). Furthermore, to avoid signal interference, two drones flying simultaneously must be at least 300 meters apart, increasing the cost and management complexity of multiple drones. While satellite remote sensing can provide free spectral information over large areas, it is limited by satellite transit times, low resolution, and interference from cloudy skies. The timeliness and accuracy of valid data are major factors limiting the application of satellite remote sensing technology for precision irrigation management in sprinkler clusters.

[0005] It can be seen that neither UAV remote sensing information nor satellite remote sensing information can be used for precise irrigation management in sprinkler clusters. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, equipment, medium and product for generating a variable irrigation prescription map based on the synergy of drones and satellite remote sensing, so as to solve the problem of being unable to perform precise irrigation management in sprinkler clusters.

[0007] To achieve the above objectives, this application provides the following solutions:

[0008] In a first aspect, the present application provides a method for generating a variable irrigation prescription map based on the synergy of drones and satellite remote sensing, comprising:

[0009] Formulate irrigation management strategies for sprinkler clusters based on the critical water requirement periods of crops, which occur during five growth stages: emergence, winter irrigation, greening and jointing, pre-flowering, and grain filling. The irrigation management strategies include whether irrigation is required and the amount of irrigation water required for each growth stage. The irrigation amount is determined based on soil moisture determined by effective rainfall and crop water consumption during different growth stages, as well as spatial variations in soil moisture deficit caused by spatial variations in soil physical and chemical properties.

[0010] Constructing a soil moisture inversion model at different growth stages based on UAV remote sensing information, and predicting and inverting the soil moisture at different growth stages based on a conversion equation between the UAV remote sensing information and satellite remote sensing information;

[0011] Based on satellite remote sensing information before the crops enter the critical water demand period of the crops, determining a spatial distribution map of soil moisture within the irrigation area of the sprinkler irrigation cluster according to the soil moisture inversion model; the satellite remote sensing information includes spectral data;

[0012] Based on the irrigation information, a spatial distribution map of water deficit within the control area of a single sprinkler irrigation device is determined according to the soil moisture inversion model and the soil moisture spatial distribution map; the irrigation information includes water source supply capacity, irrigation demand, valid data during satellite transit, and weather factors; the valid data during satellite transit is a satellite spectral image under clear weather conditions with no cloud cover;

[0013] Based on the irrigation management strategy, a variable irrigation prescription map within the control area of a single sprinkler irrigation device is determined according to the water deficit spatial distribution map; the variable irrigation prescription map includes the travel speed and irrigation amount of the sprinkler irrigation device.

[0014] In a second aspect, the present application provides a variable irrigation prescription map generation device based on the synergy of drones and satellite remote sensing, comprising:

[0015] An irrigation management strategy formulation module is used to formulate irrigation management strategies for sprinkler clusters based on the critical water demand periods of crops; the critical water demand periods of crops occur during five growth stages, including the seedling emergence stage, winter irrigation stage, greening and jointing stage, pre-flowering stage, and grain filling stage. The irrigation management strategy includes whether irrigation is required and the amount of irrigation water for each growth stage; the irrigation water amount is determined based on the soil moisture content determined by effective rainfall and crop water consumption during different growth stages, as well as the spatial variation in the degree of soil moisture deficit caused by the spatial variation of soil physical and chemical properties.

[0016] A prediction and inversion module is used to construct an inversion model of soil moisture content at different growth stages based on UAV remote sensing information, and predict and invert the soil moisture content at different growth stages based on a conversion equation between the UAV remote sensing information and satellite remote sensing information;

[0017] a soil moisture spatial distribution map determination module, configured to determine a soil moisture spatial distribution map within the irrigation area of the sprinkler irrigation cluster based on satellite remote sensing information before the crops enter the critical water demand period of the crops and according to the soil moisture inversion model; the satellite remote sensing information includes spectral data;

[0018] a water deficit spatial distribution map determination module, configured to determine a water deficit spatial distribution map within the control area of a single sprinkler irrigation device based on irrigation information, the soil moisture inversion model, and the soil moisture spatial distribution map; the irrigation information including water source supply capacity, irrigation demand, valid data during satellite transit, and weather factors; the valid data during satellite transit being satellite spectral images in clear, cloudless weather;

[0019] A variable irrigation prescription map determination module is used to determine a variable irrigation prescription map within the control area of a single sprinkler equipment based on the irrigation management strategy and the water deficit spatial distribution map; the variable irrigation prescription map includes the travel speed and irrigation volume of the sprinkler equipment.

[0020] In a third aspect, the present application provides a computer device comprising: 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 any one of the above-mentioned methods for generating variable irrigation prescription maps based on the synergy of drones and satellite remote sensing.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for generating variable irrigation prescription maps based on the synergy of drones and satellite remote sensing.

[0022] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for generating variable irrigation prescription maps based on the synergy of drones and satellite remote sensing.

[0023] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0024] This application is based on the synergy of drones and satellite remote sensing, combined with the key water-demanding growth period of crops, and fully utilizes the timeliness and accuracy of drone remote sensing on the basis of large-scale rotation irrigation decision-making based on satellite remote sensing information. By constructing soil moisture inversion models, soil moisture spatial distribution maps and water deficit spatial distribution maps at different growth stages, variable irrigation prescription maps are formulated for each sprinkler equipment in the sprinkler cluster. Since the variable irrigation prescription map is obtained by combining drone remote sensing information and satellite remote sensing information, sprinkler irrigation is carried out according to the variable irrigation prescription map to achieve precise irrigation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0026] Figure 1 This is a flow chart of a method for generating a variable irrigation prescription map based on the synergy of drones and satellite remote sensing provided in one embodiment of the present application;

[0027] Figure 2 A schematic diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0029] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0030] The embodiment of the present application provides a method for generating a variable irrigation prescription map based on the synergy of drones and satellite remote sensing. The method is executed by a computer device, specifically, it can be executed by a computer device such as a terminal or a server alone, or it can be executed by a terminal and a server together. In the embodiment of the present application, Figure 1 As shown, the method includes the following steps.

[0031] S1: Formulate irrigation management strategies for sprinkler clusters based on the critical water requirement period of crops; the critical water requirement period of crops occurs in five growth stages, including the seedling emergence stage, winter irrigation stage, greening and jointing stage, pre-flowering stage, and grain filling stage; the irrigation management strategy includes whether irrigation is required in each growth stage and the amount of irrigation water; the amount of irrigation water is determined based on the soil moisture content determined by the effective rainfall and crop water consumption in different growth stages, and the spatial variation of the degree of soil moisture deficit caused by the spatial variation of soil physical and chemical properties.

[0032] S2: Constructing a soil moisture inversion model at different growth stages based on the UAV remote sensing information, and predicting and inverting the soil moisture at different growth stages based on the conversion equation between the UAV remote sensing information and the satellite remote sensing information.

[0033] S3: Based on satellite remote sensing information before the crops enter the critical water demand period of the crops, determine the spatial distribution map of soil moisture within the irrigation area of the sprinkler cluster according to the soil moisture inversion model; the satellite remote sensing information includes spectral data.

[0034] S4: Based on the irrigation information, determine the spatial distribution map of water deficit in the control area of a single sprinkler equipment according to the soil moisture inversion model and the soil moisture spatial distribution map; the irrigation information includes the water supply capacity of the water source, irrigation demand, valid data when the satellite passes over, and weather factors; the valid data when the satellite passes over is a satellite spectral image with clear weather and no cloud cover.

[0035] S5: Based on the irrigation management strategy, determine a variable irrigation prescription map within the control area of a single sprinkler irrigation device according to the water deficit spatial distribution map; the variable irrigation prescription map includes the travel speed and irrigation amount of the sprinkler irrigation device.

[0036] In one exemplary embodiment, to determine the spatial variation of soil moisture content and its deficit within an irrigated area of more than 10,000 mu (approximately 10,000 mu), a soil moisture inversion model based on satellite remote sensing information is constructed. Considering the low accuracy of satellite remote sensing information, a conversion equation between UAV and satellite remote sensing information is first constructed. Considering the differences in remote sensing information caused by varying crop cover during different growth stages, the conversion equation between UAV and satellite remote sensing information and the construction of the soil moisture inversion model are carried out in stages. S2 can be replaced by the following steps.

[0037] S21: Based on the vegetation coverage at different growth stages, a soil moisture inversion model at different growth stages is constructed according to the UAV remote sensing information.

[0038] S22: Based on the resolution of the satellite remote sensing image, resample the spectral information in the UAV remote sensing image to the resolution scale of the satellite remote sensing image.

[0039] S23: performing linear fitting on the unified UAV spectral information and satellite spectral information to determine a conversion equation between the UAV remote sensing information and the satellite remote sensing information.

[0040] S24: Based on the conversion equation, the satellite remote sensing information is converted to UAV remote sensing accuracy, the soil moisture inversion model is called, and the inverted soil moisture is predicted.

[0041] In an exemplary embodiment, during seedling emergence and winter irrigation, because vegetation coverage is low and the planned wet layer depth is primarily concentrated in the 0-40 cm soil layer, remote sensing information can be directly used to invert the shallow soil moisture content. S21 can be replaced by the following steps.

[0042] S211: During the seedling emergence water stage and the winter irrigation stage, shallow soil moisture content, a first UAV remote sensing image, and a first satellite remote sensing image at multiple points are synchronously acquired on the same day.

[0043] S212: Using the band information in the first UAV remote sensing image as a first independent variable and the shallow soil moisture content as a first dependent variable, first UAV spectral information related to soil moisture content is filtered from the first UAV remote sensing image. The band information includes red, green, blue, red edge, and near-infrared bands.

[0044] S213: Using the first independent variable and the first dependent variable as input data and the first UAV spectral information as output data, construct a soil moisture inversion model for the seedling water stage and the winter irrigation stage.

[0045] S214: During the greening and jointing watering stage, the pre-flowering watering stage, and the grain filling watering stage, the soil moisture content, the second UAV remote sensing image, and the second satellite remote sensing image at multiple points are synchronously acquired on the same day.

[0046] S215: Determine a spectral index representing the moisture content of the plant based on the band information in the second UAV remote sensing image.

[0047] S216: Using the band information in the second UAV remote sensing image and the spectral index characterizing the plant moisture content as the second independent variable, and the soil moisture content as the second dependent variable, second UAV spectral information related to the soil moisture content is screened out from the second UAV remote sensing image.

[0048] S217: Using the second independent variable and the second dependent variable as input data and the second UAV spectral information as output data, construct a soil moisture inversion model for the greening and jointing water stage, the pre-flowering water stage, and the filling water stage.

[0049] In another exemplary embodiment, S21 may be replaced by the following steps.

[0050] (1) On the same day, shallow soil moisture content, satellite spectral images, and UAV remote sensing images were simultaneously acquired at multiple locations.

[0051] (2) The different band information (red light, green light, blue light, red edge, and near infrared) collected by UAV remote sensing is used as the independent variable, and the measured shallow soil moisture content is used as the dependent variable. The spectral data closely related to soil moisture content is screened out from the UAV remote sensing images through the LASSO regression algorithm. Then, the screened independent and dependent variables are used as input data, and a soil moisture inversion model is constructed through a machine learning model.

[0052] (3) Based on the resolution of satellite remote sensing images, the spectral data collected by UAV remote sensing are resampled and unified to the resolution scale of satellite remote sensing images. The i spectral data closely related to soil moisture content obtained from UAV remote sensing in step (2) are respectively used as y i , the corresponding spectral data of the same type obtained from satellite remote sensing is taken as x i , by fitting y i with x i The linear equations between them are used to establish the transformation equations of UAV remote sensing and satellite remote sensing information respectively.

[0053] (4) After the conversion equation is established to the UAV remote sensing accuracy, the soil moisture inversion model established in (2) can be called to predict and invert the soil moisture content.

[0054] In one exemplary embodiment, during watering during greening and jointing, pre-flowering, and grain filling, due to high vegetation coverage, there is a strong correlation between soil moisture content in the 0-60 cm range and plant moisture content. Remote sensing information can be used to directly invert soil moisture. S3 can be replaced by the following steps.

[0055] S31: Obtain satellite remote sensing images of the crop before it enters its critical water demand period, and select a satellite remote sensing image corresponding to the most recent satellite transit date that satisfies clear weather conditions and no cloud cover. For example, the most recent Sentinel-2 transit date that satisfies clear weather conditions and no cloud cover is selected, and the satellite remote sensing image is downloaded from a corresponding website to extract spectral data.

[0056] S32: extracting spectral data of the satellite remote sensing image, and transforming the spectral data based on the transformation equation to determine transformed spectral data.

[0057] S33: Inputting the converted spectral data into the soil moisture inversion model to predict the soil moisture content within the irrigation area of the inversion sprinkler irrigation cluster.

[0058] S34: Based on the soil moisture content in the irrigation area of the sprinkler irrigation cluster, draw a spatial distribution map of the soil moisture content in the irrigation area of the sprinkler irrigation cluster using ArcGIS software.

[0059] In another exemplary embodiment, S3 may be replaced by the following steps.

[0060] (1) On the same day, soil moisture, satellite spectral images, and UAV remote sensing images were simultaneously acquired at multiple locations.

[0061] (2) The different band information collected by UAV remote sensing and the spectral indices representing plant moisture content composed of these band information (for example, Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Optimization of Soil Regulatory Vegetation Index (OSAVI), Enhanced Vegetation Index (EVI)) are used as independent variables, and the measured soil moisture content is used as the dependent variable. The spectral data closely related to soil moisture content are screened out through the LASSO regression algorithm. Then, the screened independent and dependent variables are used as input data, and a soil moisture inversion model is constructed through a machine learning model.

[0062] (3) Based on the resolution of satellite remote sensing images, the spectral data collected by UAV remote sensing are resampled and unified to the resolution scale of satellite remote sensing images. The i spectral data closely related to soil moisture content obtained from UAV remote sensing in step (2) are respectively used as y i , the corresponding spectral data of the same type obtained from satellite remote sensing is taken as x i , by fitting y i with x i The linear equations between them are used to establish the transformation equations of UAV remote sensing and satellite remote sensing information respectively.

[0063] (4) After the satellite remote sensing information is converted to the UAV remote sensing accuracy through the conversion equation established in (3), the soil moisture inversion model established in (2) can be called to predict and invert the soil moisture content.

[0064] In an exemplary embodiment, S4 may be replaced by the following steps.

[0065] S41: If the water supply capacity of the water source cannot simultaneously meet the irrigation needs of all sprinkler irrigation equipment, the average soil moisture content in the control area of a single sprinkler irrigation equipment is calculated based on the spatial distribution map of soil moisture content.

[0066] S42: sorting the average soil moisture content in the area controlled by the single sprinkler irrigation equipment, and formulating a rotation irrigation system for the sprinkler irrigation cluster according to the sorting result.

[0067] S43: Based on the rotation irrigation system, within the area controlled by a single sprinkler equipment that needs to be irrigated, if there is valid data when the satellite passes over on the day of irrigation or two days before irrigation, the spectral data corresponding to the valid data is converted based on the conversion equation, and the converted spectral data is input into the soil moisture inversion model to predict the first soil moisture content within the inverted irrigation area; the irrigation area is the area controlled by a single irrigation equipment.

[0068] S44: Calculate a first difference between the first soil moisture content and the irrigation upper limit, and generate a water deficit spatial distribution map of the irrigation area according to the first difference.

[0069] S45: If the satellite data is invalid due to weather factors, the required spectral data is filtered based on the spectral data of the soil or canopy obtained by the drone remote sensing system within a set time period two days before irrigation or on the day of irrigation. The set time period is 11:00 to 16:00.

[0070] S46: Inputting the required spectral data into the soil moisture inversion model to predict a second soil moisture content in the inversion irrigation area.

[0071] S47: Calculate a second difference between the second soil moisture content and the irrigation upper limit, and generate a water deficit spatial distribution map of the irrigation area according to the second difference.

[0072] S48: If the water supply capacity of the water source can simultaneously meet the irrigation needs of all sprinkler irrigation equipment, the difference between the third soil moisture content and the irrigation upper limit is calculated according to the spatial distribution map of soil moisture content to generate a spatial distribution map of water deficit in the irrigation area; the first soil moisture content, the second soil moisture content and the third soil moisture content are the soil moisture contents within the planned moist layer.

[0073] In an exemplary embodiment, S5 may be replaced by the following steps.

[0074] S51: Based on the irrigation management strategy, according to the water deficit spatial distribution map and the range of the sprinkler equipment, the control area of each sprinkler equipment is divided into rectangular grids of different lengths or fan-shaped grids of different angles that are greater than the range of the sprinkler head as variable irrigation management areas along the travel direction.

[0075] S52: Calculating the average soil moisture deficit of each variable irrigation management area based on the water deficit spatial distribution map.

[0076] S53: Determine the irrigation amount of each variable irrigation management area according to the average soil moisture deficit and the planned depth of the moist layer.

[0077] S54: Determine a variable irrigation prescription map within the control area of a single sprinkler irrigation device according to the irrigation amount and the travel speed of each sprinkler irrigation device.

[0078] In another exemplary embodiment, S5 may be replaced by the following steps.

[0079] According to the complexity of the spatial distribution map of water deficit in the irrigation area and taking into account the range of the sprinkler equipment, the control area of each sprinkler equipment is divided into rectangular grids of different lengths (translational sprinklers, reel sprinklers) or fan-shaped grids of different angles (circular sprinklers) along its travel direction that are larger than the sprinkler range as variable irrigation management areas. Based on the spatial distribution map of water deficit within the control area of a single sprinkler equipment, the average soil moisture deficit is calculated in each management area, and the irrigation amount W in each management area is calculated by multiplying it by the planned wet layer depth. 灌 :

[0080] W 灌 =(⊙ 上限 -⊙ 土 )×h;

[0081] Among them, W 灌 is the irrigation volume of the management area, mm; 上限 is the upper limit of soil moisture content in the management area, cm 3 / cm 3 ⊙ 土 is the average soil moisture content in the management area, cm 3 / cm 3 ; h is the planned wet layer depth, mm.

[0082] A GPS positioning system and an automatic control system for adjusting the travel speed are installed on each sprinkler equipment. When entering the boundary of each management area, watering is achieved by automatically adjusting the travel speed of the sprinkler equipment. The code composed of different sprinkler equipment travel speeds in different management areas is the variable irrigation prescription map of the sprinkler area.

[0083] Based on the same inventive concept, embodiments of the present application also provide a device for generating a variable-rate irrigation prescription map based on the synergy of drones and satellite remote sensing, which is used to implement the aforementioned method for generating a variable-rate irrigation prescription map based on the synergy of drones and satellite remote sensing. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for generating a variable-rate irrigation prescription map based on the synergy of drones and satellite remote sensing provided below can be found in the above-mentioned limitations of the method for generating a variable-rate irrigation prescription map based on the synergy of drones and satellite remote sensing, and will not be further elaborated here.

[0084] In an exemplary embodiment, a variable irrigation prescription map generation device based on the synergy of drones and satellite remote sensing is provided, comprising:

[0085] The irrigation management strategy formulation module is used to formulate irrigation management strategies for sprinkler clusters based on the critical water requirement period of crops; the critical water requirement period of crops occurs in five growth stages, which include the seedling emergence water stage, winter irrigation stage, greening and jointing water stage, pre-flowering water stage and grain filling water stage; the irrigation management strategy includes whether irrigation is required in each growth stage and the amount of irrigation water; the irrigation water amount is determined based on the soil moisture content determined by the effective rainfall and crop water consumption in different growth stages, and the spatial variation of the soil moisture deficit caused by the spatial variation of soil physical and chemical properties.

[0086] The prediction and inversion module is used to construct an inversion model of soil moisture content at different growth stages based on UAV remote sensing information, and predict and invert the soil moisture content at different growth stages based on the conversion equation between the UAV remote sensing information and satellite remote sensing information.

[0087] A soil moisture spatial distribution map determination module is used to determine the soil moisture spatial distribution map within the irrigation area of the sprinkler cluster based on satellite remote sensing information before the crops enter the critical water demand period of the crops and according to the soil moisture inversion model; the satellite remote sensing information includes spectral data.

[0088] A water deficit spatial distribution map determination module is used to determine the water deficit spatial distribution map within the control area of a single sprinkler irrigation device based on irrigation information, the soil moisture inversion model, and the soil moisture spatial distribution map; the irrigation information includes water source supply capacity, irrigation demand, valid data during satellite transit, and weather factors; the valid data during satellite transit is a satellite spectral image of clear weather without cloud cover.

[0089] A variable irrigation prescription map determination module is used to determine a variable irrigation prescription map within the control area of a single sprinkler equipment based on the irrigation management strategy and the water deficit spatial distribution map; the variable irrigation prescription map includes the travel speed and irrigation volume of the sprinkler equipment.

[0090] This application combines the time period of the critical water demand period of crops, fully utilizes the timeliness and accuracy advantages of drone remote sensing to make large-scale rotation irrigation decisions based on satellite remote sensing information, and formulates a variable irrigation prescription map for a single sprinkler equipment.

[0091] In an exemplary embodiment, a computer device is provided, such as Figure 2 As shown, the computer device can be a server or a terminal. The computer device includes a processor, a memory, an input / output (I / O) interface, and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data for generating variable irrigation prescription maps based on the synergy of unmanned aerial vehicles and satellite remote sensing. The I / O interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via a network connection. When executed by the processor, the computer program implements a method for generating variable irrigation prescription maps based on the synergy of unmanned aerial vehicles and satellite remote sensing.

[0092] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0093] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above method when executed by a processor.

[0094] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0095] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0096] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0097] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0098] 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.

[0099] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing, characterized in that: The variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing includes: Formulate irrigation management strategies for sprinkler clusters based on the critical water requirement periods of crops, which occur during five growth stages: emergence, winter irrigation, greening and jointing, pre-flowering, and grain filling. The irrigation management strategies include whether irrigation is required and the amount of irrigation water required for each growth stage. The irrigation amount is determined based on soil moisture determined by effective rainfall and crop water consumption during different growth stages, as well as spatial variations in soil moisture deficit caused by spatial variations in soil physical and chemical properties. A soil moisture inversion model for different growth stages is constructed based on the UAV remote sensing information, and the soil moisture content for different growth stages is predicted and inverted based on a conversion equation between the UAV remote sensing information and the satellite remote sensing information; wherein, the soil moisture inversion model for different growth stages is constructed based on the UAV remote sensing information, specifically including: During the seedling emergence water stage and the winter irrigation stage, simultaneously acquiring shallow soil moisture content, a first UAV remote sensing image, and a first satellite remote sensing image at multiple points on the same day; Using the band information in the first UAV remote sensing image as a first independent variable and the shallow soil moisture content as a first dependent variable, first UAV spectral information related to soil moisture content is screened out from the first UAV remote sensing image; Using the first independent variable and the first dependent variable as input data and the first UAV spectral information as output data, constructing a soil moisture inversion model for the seedling emergence water stage and the winter irrigation stage; During the greening and jointing watering stage, the pre-flowering watering stage, and the grain filling watering stage, synchronously acquiring soil moisture content, a second UAV remote sensing image, and a second satellite remote sensing image at multiple points on the same day; determining a spectral index representing the moisture content of the plant based on the band information in the second UAV remote sensing image; Using the band information in the second UAV remote sensing image and the spectral index representing the plant moisture content as a second independent variable, and the soil moisture content as a second dependent variable, filtering out the second UAV spectral information related to the soil moisture content from the second UAV remote sensing image; Using the second independent variable and the second dependent variable as input data and the second drone spectral information as output data, constructing a soil moisture inversion model for the greening and jointing water stage, the pre-flowering water stage, and the grain filling water stage; Based on satellite remote sensing information before the crops enter the critical water demand period of the crops, determining a spatial distribution map of soil moisture within the irrigation area of the sprinkler irrigation cluster according to the soil moisture inversion model; the satellite remote sensing information includes spectral data; Based on the irrigation information, a spatial distribution map of water deficit within the control area of a single sprinkler irrigation device is determined according to the soil moisture inversion model and the soil moisture spatial distribution map; the irrigation information includes water source supply capacity, irrigation demand, valid data during satellite transit, and weather factors; the valid data during satellite transit is a satellite spectral image under clear weather conditions with no cloud cover; Based on the irrigation management strategy, a variable irrigation prescription map within the control area of a single sprinkler irrigation device is determined according to the water deficit spatial distribution map; the variable irrigation prescription map includes the travel speed and irrigation amount of the sprinkler irrigation device.

2. The variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing according to claim 1 is characterized in that: Based on the UAV remote sensing information, a soil moisture inversion model for different growth stages is constructed. Based on the conversion equation between the UAV remote sensing information and the satellite remote sensing information, the soil moisture content at different growth stages is predicted and inverted, specifically including: Based on the vegetation coverage at different growth stages, a soil moisture inversion model at different growth stages is constructed according to the UAV remote sensing information; Based on the resolution of the satellite remote sensing image, resampling the spectral information in the UAV remote sensing image to the resolution scale of the satellite remote sensing image; Performing linear fitting on the unified UAV spectral information and satellite spectral information to determine a conversion equation between the UAV remote sensing information and the satellite remote sensing information; Based on the conversion equation, the satellite remote sensing information is converted to UAV remote sensing accuracy, and the soil moisture inversion model is called to predict and invert the soil moisture.

3. The variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing according to claim 2 is characterized in that: Based on satellite remote sensing information before the crops enter the critical water demand period of the crops, a spatial distribution map of soil moisture within the irrigation area of the sprinkler irrigation cluster is determined according to the soil moisture inversion model, specifically including: Obtaining satellite remote sensing images of crops before they enter a critical water-demand period, and selecting satellite remote sensing images corresponding to the most recent satellite transit date that satisfies clear weather conditions with no cloud cover; Extracting spectral data of the satellite remote sensing image, and transforming the spectral data based on the transformation equation to determine transformed spectral data; Inputting the converted spectral data into the soil moisture inversion model to predict the soil moisture content within the irrigation area of the inverted sprinkler irrigation cluster; Based on the soil moisture content within the sprinkler irrigation cluster irrigation area, ArcGIS software is used to draw a spatial distribution map of the soil moisture content within the sprinkler irrigation cluster irrigation area.

4. The variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing according to claim 2 is characterized in that: Based on the irrigation information, determining the water deficit spatial distribution map within the control area of a single sprinkler irrigation device according to the soil moisture inversion model and the soil moisture spatial distribution map specifically includes: If the water supply capacity of the water source cannot simultaneously meet the irrigation needs of all sprinkler irrigation equipment, the average soil moisture content in the control area of a single sprinkler irrigation equipment is calculated based on the spatial distribution map of soil moisture content; sorting the average soil moisture content within the control area of the single sprinkler irrigation equipment, and formulating a rotation irrigation system for the sprinkler irrigation cluster according to the sorting results; Based on the rotation irrigation system, within the area controlled by a single sprinkler irrigation device that needs to be irrigated, if there is valid data from a satellite transit on the day of irrigation or two days before irrigation, spectral data corresponding to the valid data is converted based on the conversion equation, and the converted spectral data is input into the soil moisture inversion model to predict a first soil moisture content within the inverted irrigation area; the irrigation area is the area controlled by the single sprinkler irrigation device; calculating a first difference between the first soil moisture content and an upper limit of irrigation, and generating a spatial distribution map of water deficit in the irrigation area according to the first difference; If the satellite data are invalid due to weather factors, the required spectral data are filtered out based on the spectral data of the soil or canopy obtained within a set time period two days before irrigation or on the day of irrigation using a UAV remote sensing system; Inputting the required spectral data into the soil moisture inversion model to predict a second soil moisture content in the inverted irrigation area; calculating a second difference between the second soil moisture content and the irrigation upper limit, and generating a water deficit spatial distribution map of the irrigation area according to the second difference; If the water supply capacity of the water source can simultaneously meet the irrigation needs of all sprinkler irrigation equipment, the difference between the third soil moisture content and the irrigation upper limit is calculated according to the spatial distribution map of soil moisture content to generate a spatial distribution map of water deficit in the irrigation area; the first soil moisture content, the second soil moisture content and the third soil moisture content are the soil moisture contents within the planned moist layer.

5. The variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing according to claim 1 is characterized in that: Based on the irrigation management strategy, a variable irrigation prescription map within the control area of a single sprinkler irrigation device is determined according to the water deficit spatial distribution map, specifically including: Based on the irrigation management strategy, according to the water deficit spatial distribution map and the range of the sprinkler equipment, the control area of each sprinkler equipment is divided into rectangular grids of different lengths or fan-shaped grids of different angles that are greater than the range of the sprinkler head as variable irrigation management areas along the travel direction; Calculating the average soil moisture deficit in each variable irrigation management area based on the water deficit spatial distribution map; determining the irrigation amount of each variable irrigation management area according to the average soil moisture deficit and the depth of the planned moist layer; A variable irrigation prescription map within the control area of a single sprinkler irrigation device is determined according to the irrigation amount and the travel speed of each sprinkler irrigation device.

6. A variable irrigation prescription map generation device based on the synergy of drones and satellite remote sensing, characterized in that: The variable irrigation prescription map generation device based on the synergy of UAV and satellite remote sensing adopts the variable irrigation prescription map generation method based on the synergy of UAV and satellite remote sensing according to any one of claims 1 to 5, and the variable irrigation prescription map generation device based on the synergy of UAV and satellite remote sensing comprises: An irrigation management strategy formulation module is used to formulate irrigation management strategies for sprinkler clusters based on the critical water demand periods of crops; the critical water demand periods of crops occur during five growth stages, including the seedling emergence stage, winter irrigation stage, greening and jointing stage, pre-flowering stage, and grain filling stage. The irrigation management strategy includes whether irrigation is required and the amount of irrigation water for each growth stage; the irrigation water amount is determined based on the soil moisture content determined by effective rainfall and crop water consumption during different growth stages, as well as the spatial variation in the degree of soil moisture deficit caused by the spatial variation of soil physical and chemical properties. A prediction and inversion module is used to construct an inversion model of soil moisture content at different growth stages based on UAV remote sensing information, and predict and invert the soil moisture content at different growth stages based on a conversion equation between the UAV remote sensing information and satellite remote sensing information; a soil moisture spatial distribution map determination module, configured to determine a soil moisture spatial distribution map within the irrigation area of the sprinkler irrigation cluster based on satellite remote sensing information before the crops enter the critical water demand period of the crops and according to the soil moisture inversion model; the satellite remote sensing information includes spectral data; a water deficit spatial distribution map determination module, configured to determine a water deficit spatial distribution map within the control area of a single sprinkler irrigation device based on irrigation information, the soil moisture inversion model, and the soil moisture spatial distribution map; the irrigation information including water source supply capacity, irrigation demand, valid data during satellite transit, and weather factors; the valid data during satellite transit being satellite spectral images in clear, cloudless weather; A variable irrigation prescription map determination module is used to determine a variable irrigation prescription map within the control area of a single sprinkler equipment based on the irrigation management strategy and the water deficit spatial distribution map; the variable irrigation prescription map includes the travel speed and irrigation volume of the sprinkler equipment.

7. A computer device comprising: 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 variable irrigation prescription map generation method based on the synergy of drone and satellite remote sensing according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating a variable irrigation prescription map based on the synergy of unmanned aerial vehicle and satellite remote sensing according to any one of claims 1 to 5 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating a variable irrigation prescription map based on the synergy of unmanned aerial vehicle and satellite remote sensing according to any one of claims 1 to 5 is implemented.

Images