Unmanned farm operation data supervision system and method based on three-dimensional view

Abstract

The invention discloses an unmanned farm operation data supervision system and method based on a three-dimensional view, and relates to the technical field of agricultural data supervision, and the unmanned farm operation data supervision method specifically comprises the following steps: collecting unmanned aerial vehicle operation data and farm environment data; a farm dynamic digital twinborn model is constructed, and unmanned aerial vehicle operation quality data, soil moisture content data and crop growth data are displayed in real time; according to the dynamic digital twin model of the farm, analyzing a corresponding relation between the operation track data of the unmanned aerial vehicle and the crop growth data; and quantifying the operation effect of the unmanned aerial vehicle by comparing the crop growth data at different times, and performing automatic supervision on the operation of the unmanned aerial vehicle according to the corresponding relationship between the operation track data of the unmanned aerial vehicle and the crop growth data. By analyzing the corresponding relation between the unmanned aerial vehicle operation track data and the crop growth data, the influence of the operation parameters on the crop growth quality is effectively analyzed, and the quantitative evaluation of the operation effect is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural data supervision, and in particular to an unmanned farm operation data supervision system and method based on three-dimensional views. Background Art

[0002] Agricultural data supervision technology refers to the process of comprehensively collecting, integrating and intelligently analyzing operation data, environmental data and crop growth data using technologies such as the Internet of Things, remote sensing and drones throughout the entire agricultural production process, aiming to achieve visualization, refinement and intelligent management of agricultural operations.

[0003] With the continuous and in-depth development of intelligent and refined agricultural management, the application of drones in farm operations has become more and more common. In the operation links such as sowing, pesticide application, and surveying, drones have shown extremely high efficiency and are very flexible in operation. At the same time, the continuous advancement of technologies such as sensors, remote sensing images, and GPS positioning has made the collection of farm environmental information more comprehensive and real-time, laying a data foundation for digital agricultural management. However, most existing agricultural management systems are limited to recording a single type of data, or adopt a decentralized environmental monitoring method. These systems have failed to systematically build a relationship model between drone operation behavior, farmland environmental changes, and crop growth results, and lack in-depth analysis. In addition, most traditional systems use two-dimensional maps or static charts to present farm information, which makes it difficult to reflect spatial characteristics such as terrain differences, crop distribution, and soil conditions, and it is impossible to update the operation status in real time, which makes supervision lack of intuitiveness. Summary of the invention

[0004] The purpose of the present invention is to provide an unmanned farm operation data supervision system and method based on three-dimensional views to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for supervising unmanned farm operation data based on three-dimensional view, the method specifically comprising the following steps: Step S100, collecting drone operation data and farm environment data; the drone operation data includes drone operation trajectory data and drone operation quality data; the farm environment data includes farm basic data, soil moisture data and crop growth data; Step S200: Based on the basic farm data, the drone operation trajectory data is superimposed to build a dynamic digital twin model of the farm, and the drone operation quality data, soil moisture data and crop growth data are displayed in real time; Step S300: analyzing the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; Step S400: quantify the effect of the drone operation by comparing the crop growth data at different times, and automatically supervise the drone operation according to the corresponding relationship between the drone operation trajectory data and the crop growth data.

[0006] In step S100, drone operation data and farm environment data are collected, specifically: The drone operation data includes drone operation trajectory data and drone operation quality data; The farm environment data includes basic farm data, soil moisture data and crop growth data; The drone is equipped with a GPS positioning device, which obtains the location of the drone at certain time intervals to obtain the operation trajectory data of the drone; Install various sensors on drones to monitor the quality of work; Install pesticide spraying monitoring sensors to monitor the flow rate, pressure and other parameters of pesticide spraying in real time to determine whether the spraying is uniform and whether the set spraying amount is reached; for sowing operations, monitor the density and uniformity of sowing by installing visual sensors or weight sensors.

[0007] Obtaining basic farm data through satellite images, wherein the basic farm data includes the boundaries, areas and topographic data of different crops on the farm; The soil moisture data is obtained by deploying soil moisture sensors in a grid-like manner; Use drones to regularly capture multispectral images of crops and obtain crop growth data.

[0008] The crop growth data is obtained by measuring the plant height, coverage, color and other characteristics of the crop through image analysis software; Data transmission through LoRaWAN networking; In step S200, the basic farm data is used as the basis, and the drone operation trajectory data is superimposed to construct a farm dynamic digital twin model, which displays the drone operation quality data, soil moisture data and crop growth data in real time, specifically: Based on the time of collecting drone operation data and farm environment data, temporal and spatial alignment is performed; Display the boundaries, area and topographic data of different crops on the farm through a three-dimensional grid; The GPS positioning device equipped on the drone can display the current drone operation track and update it in real time; Real-time display of drone operation quality data corresponding to the drone operation trajectory; Soil moisture data is indicated by color gradient; The crop growth curve over time is drawn through crop growth data for visual display.

[0009] In step S300, the corresponding relationship between the drone operation trajectory data and the crop growth data is analyzed according to the farm dynamic digital twin model, specifically: Step S301, dividing the farm into grid units of equal area, and recording the location, crop type and crop quantity of each unit; Step S302: According to the farm dynamic digital twin model, obtain the drone operation parameters O(x, y, t), and collect the crop growth data G(x, y, t+Δt) after a period of time Δt; wherein x and y represent the horizontal coordinate and vertical coordinate of the drone operation trajectory respectively; t represents the time mark of the acquisition; Step S303, obtaining several groups of the UAV operation parameters O(x, y, t) and crop growth data G(x, y, t+Δt) after a period of time Δt, performing data fitting, and obtaining estimation relationship functions between different crop growth data and the UAV operation parameters respectively; Step S304: Consider the impact of neighborhood effect on crops in adjacent grid cells, obtain neighborhood effect correction terms, and perform spatial coupling.

[0010] In step S400, the effect of the drone operation is quantified by comparing the crop growth data at different times, and the drone operation is automatically supervised according to the corresponding relationship between the drone operation trajectory data and the crop growth data, specifically: Step S401: taking the current crop growth data as a benchmark, collecting the crop growth data after a period of time, comparing the crop growth data at different times, and extracting the structural change index of the crop growth; Step S402: Automated supervision of the drone operation is performed based on the correspondence between the drone operation trajectory data and the crop growth data.

[0011] An unmanned farm operation data supervision system based on three-dimensional views, the unmanned farm operation data supervision system comprising a data acquisition module, a data processing module, a digital twin modeling module, a data analysis module and a data supervision and visualization module; The data acquisition module is used to collect drone operation data and farm environment data; The data processing module is used to align the timestamps of the collected UAV operation data with the farm environment data to provide continuous data; The digital twin modeling module is used to build a dynamic digital twin model of the farm based on the basic farm data and superimpose the drone operation trajectory data, and to display the drone operation quality data, soil moisture data and crop growth data in real time; The data analysis module is used to analyze the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; The data supervision and visualization module is used to compare crop growth data at different times, quantify the effect of drone operations, automatically supervise drone operations based on the correspondence between the drone operation trajectory data and crop growth data, and visualize the growth curve of crops over time.

[0012] The data acquisition module includes a drone operation data unit, a farm environment data unit and a data transmission unit; The drone operation data unit is used to obtain drone operation data, and the drone operation data includes drone operation trajectory data and drone operation quality data; The farm environment data unit is used to obtain farm environment data, and the farm environment data includes basic farm data, soil moisture data and crop growth data; The data transmission unit is used for long-distance data transmission via LoRaWAN.

[0013] Specifically: Back up the collected drone operation data, farm environment data and crop growth curves over time; The crop growth curve over time supports playback.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention can systematically integrate drone operation data and farm environment data, construct a dynamic and spatialized digital twin model, and realize full-process, visualized, and intelligent supervision of farm operations. By aligning the drone operation trajectory, operation quality parameters, soil moisture, crop growth and other data in time and space and superimposing them in three dimensions, it not only improves the intuitive display ability of the operation process, but also can dynamically reflect the farm status in real time, making up for the limitations of traditional two-dimensional chart display. In addition, the present invention establishes a quantitative correlation model between operation behavior and crop growth results, and introduces a neighborhood coupling mechanism to effectively analyze the impact of operation parameters on crop growth quality and realize quantitative evaluation of operation results. At the same time, the present invention also has the ability to analyze the difference of crop data changes, supports the identification of abnormal operation areas, and thus significantly improves the supervision efficiency. The present invention effectively improves the level of intelligent data supervision of unmanned farm operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of an unmanned farm operation data supervision method based on three-dimensional view of the present invention; Figure 2 This is a schematic diagram of the structure of an unmanned farm operation data monitoring system based on a three-dimensional view according to the present invention; Figure 3 It is a visualized schematic diagram of the dynamic growth curve and automated supervision of crops in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example: Figure 1-Figure 3 As shown, the present invention provides a technical solution, a method for supervising unmanned farm operation data based on a three-dimensional view, and the method for supervising unmanned farm operation data specifically comprises the following steps: Step S100, collecting drone operation data and farm environment data; the drone operation data includes drone operation trajectory data and drone operation quality data; the farm environment data includes farm basic data, soil moisture data and crop growth data; Step S200: Based on the basic farm data, the drone operation trajectory data is superimposed to build a dynamic digital twin model of the farm, and the drone operation quality data, soil moisture data and crop growth data are displayed in real time; Step S300: analyzing the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; Step S400: quantify the effect of the drone operation by comparing the crop growth data at different times, and automatically supervise the drone operation according to the corresponding relationship between the drone operation trajectory data and the crop growth data.

[0018] In step S100, drone operation data and farm environment data are collected, specifically: The drone operation data includes drone operation trajectory data and drone operation quality data; The farm environment data includes basic farm data, soil moisture data and crop growth data; The drone is equipped with a GPS positioning device, which obtains the location of the drone at certain time intervals to obtain the operation trajectory data of the drone; Install various sensors on drones to monitor the quality of work; Install pesticide spraying monitoring sensors to monitor the flow rate, pressure and other parameters of pesticide spraying in real time to determine whether the spraying is uniform and whether the set spraying amount is reached; for sowing operations, monitor the density and uniformity of sowing by installing visual sensors or weight sensors.

[0019] Obtaining basic farm data through satellite images, wherein the basic farm data includes the boundaries, areas and topographic data of different crops on the farm; The soil moisture data is obtained by deploying soil moisture sensors in a grid-like manner; Use drones to regularly capture multispectral images of crops and obtain crop growth data.

[0020] The crop growth data is obtained by measuring the plant height, coverage, color and other characteristics of the crop through image analysis software; Data transmission through LoRaWAN networking; In step S200, the basic farm data is used as the basis, and the drone operation trajectory data is superimposed to construct a farm dynamic digital twin model, which displays the drone operation quality data, soil moisture data and crop growth data in real time, specifically: Based on the time of collecting drone operation data and farm environment data, temporal and spatial alignment is performed; Display the boundaries, area and topographic data of different crops on the farm through a three-dimensional grid; The GPS positioning device equipped on the drone can display the current drone operation track and update it in real time; Real-time display of drone operation quality data corresponding to the drone operation trajectory; Soil moisture data is indicated by color gradient; The crop growth curve over time is drawn through crop growth data for visual display.

[0021] In step S300, the corresponding relationship between the drone operation trajectory data and the crop growth data is analyzed according to the farm dynamic digital twin model, specifically: Step S301, dividing the farm into grid units of equal area, and recording the location, crop type and crop quantity of each unit; Step S302: According to the farm dynamic digital twin model, obtain the drone operation parameters O(x, y, t), and collect the crop growth data G(x, y, t+Δt) after a period of time Δt; wherein x and y represent the horizontal coordinate and vertical coordinate of the drone operation trajectory respectively; t represents the time mark of the acquisition; Step S303, obtaining several groups of the UAV operation parameters O(x, y, t) and crop growth data G(x, y, t+Δt) after a period of time Δt, performing data fitting, and obtaining estimation relationship functions between different crop growth data and the UAV operation parameters respectively; Step S304: Consider the impact of neighborhood effect on crops in adjacent grid cells, obtain neighborhood effect correction terms, and perform spatial coupling.

[0022] In step S400, the effect of the drone operation is quantified by comparing the crop growth data at different times, and the drone operation is automatically supervised according to the corresponding relationship between the drone operation trajectory data and the crop growth data, specifically: Step S401: taking the current crop growth data as a benchmark, collecting the crop growth data after a period of time, comparing the crop growth data at different times, and extracting the structural change index of the crop growth; Step S402: Automated supervision of the drone operation is performed based on the correspondence between the drone operation trajectory data and the crop growth data.

[0023] An unmanned farm operation data supervision system based on three-dimensional views, the unmanned farm operation data supervision system comprising a data acquisition module, a data processing module, a digital twin modeling module, a data analysis module and a data supervision and visualization module; The data acquisition module is used to collect drone operation data and farm environment data; The data processing module is used to align the timestamps of the collected UAV operation data with the farm environment data to provide continuous data; The digital twin modeling module is used to build a dynamic digital twin model of the farm based on the basic farm data and superimpose the drone operation trajectory data, and to display the drone operation quality data, soil moisture data and crop growth data in real time; The data analysis module is used to analyze the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; The data supervision and visualization module is used to compare crop growth data at different times, quantify the effect of drone operations, automatically supervise drone operations based on the correspondence between the drone operation trajectory data and crop growth data, and visualize the growth curve of crops over time.

[0024] The data acquisition module includes a drone operation data unit, a farm environment data unit and a data transmission unit; The drone operation data unit is used to obtain drone operation data, and the drone operation data includes drone operation trajectory data and drone operation quality data; The farm environment data unit is used to obtain farm environment data, and the farm environment data includes basic farm data, soil moisture data and crop growth data; The data transmission unit is used for long-distance data transmission via LoRaWAN.

[0025] Specifically: Back up the collected drone operation data, farm environment data and crop growth curves over time; The crop growth curve over time supports playback.

[0026] Example Step S100, collecting drone operation data and farm environment data; the drone operation data includes drone operation trajectory data and drone operation quality data; the farm environment data includes farm basic data, soil moisture data and crop growth data; Step S200: Based on the basic farm data, the drone operation trajectory data is superimposed to build a dynamic digital twin model of the farm, and the drone operation quality data, soil moisture data and crop growth data are displayed in real time; Step S300: analyzing the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; Step S400: quantify the effect of the drone operation by comparing the crop growth data at different times, and automatically supervise the drone operation according to the corresponding relationship between the drone operation trajectory data and the crop growth data.

[0027] In step S100, drone operation data and farm environment data are collected, specifically: The drone operation data includes drone operation trajectory data and drone operation quality data; The farm environment data includes basic farm data, soil moisture data and crop growth data; The drone is equipped with a GPS positioning device, which obtains the location of the drone at certain time intervals to obtain the operation trajectory data of the drone; Install various sensors on drones to monitor the quality of work; Install pesticide spraying monitoring sensors to monitor the flow rate, pressure and other parameters of pesticide spraying in real time to determine whether the spraying is uniform and whether the set spraying amount is reached; for sowing operations, monitor the density and uniformity of sowing by installing visual sensors or weight sensors.

[0028] Obtaining basic farm data through satellite images, wherein the basic farm data includes the boundaries, areas and topographic data of different crops on the farm; The soil moisture data is obtained by deploying soil moisture sensors in a grid-like manner; Wherein, the soil moisture data is standardized; As a preference, the standardization method may use a Max-Min standardization method; Use drones to regularly capture multispectral images of crops and obtain crop growth data.

[0029] The crop growth data is obtained by measuring the plant height, coverage, color and other characteristics of the crop through image analysis software; Data transmission through LoRaWAN networking; In step S200, the basic farm data is used as the basis, and the drone operation trajectory data is superimposed to construct a farm dynamic digital twin model, which displays the drone operation quality data, soil moisture data and crop growth data in real time, specifically: Based on the time of collecting drone operation data and farm environment data, temporal and spatial alignment is performed; Display the boundaries, area and topographic data of different crops on the farm through a three-dimensional grid; The GPS positioning device equipped on the drone can display the current drone operation track and update it in real time; Real-time display of drone operation quality data corresponding to the drone operation trajectory; Soil moisture data is indicated by color gradient; The crop growth curve over time is drawn through crop growth data for visual display.

[0030] In step S300, the corresponding relationship between the drone operation trajectory data and the crop growth data is analyzed according to the farm dynamic digital twin model, specifically: Step S301, dividing the farm into grid units of equal area, and recording the location, crop type and crop quantity of each unit; Step S302: According to the farm dynamic digital twin model, obtain the drone operation parameters O(x, y, t), and collect the crop growth data G(x, y, t+Δt) after a period of time Δt; wherein x and y represent the horizontal coordinate and vertical coordinate of the drone operation trajectory respectively; t represents the time mark of the acquisition; Step S303, obtaining several groups of the UAV operation parameters O(x, y, t) and crop growth data G(x, y, t+Δt) after a period of time Δt, performing data fitting, and obtaining estimation relationship functions between different crop growth data and the UAV operation parameters respectively; Wherein, the expression paradigm of the estimation relationship function is: ; Where G represents crop growth data; It represents the mapping relationship of the fitting function with the UAV operation parameter O and the environmental factor E as parameters; E represents the environmental factor; Among them, the crop growth data G includes crop height, leaf density and crop yield, etc.; the environmental factors E include soil moisture, flow and pressure data of pesticide spraying and fertilization data, etc.; taking corn variable fertilization as an example, the crop growth data G selects corn yield; the environmental factors E that affect corn yield include effective fertilizer amount and soil moisture, that is, Y∈G; W, ∈E; get the following estimation relationship function: ;in, Represents the corn yield at the coordinate (x,y); Indicates the maximum production in history; It represents the effective amount of fertilizer, which is obtained by the pesticide spraying monitoring sensor installed on the drone. The flow and pressure data of pesticide spraying are monitored in real time, and the ratio of the current monitoring data to the normal value is used as the effective amount of fertilizer; e represents a natural constant; Indicates the average soil moisture content over a period of time; Indicates the soil moisture threshold suitable for crop growth, preferably corn planting, ; and s represent the smoothing coefficients of soil fertilizer application and soil moisture, respectively. As a preferred option, k=0.025; s=0.3; The uniformity of crop height is fitted with the flight parameters of the drone during sowing, specifically: ;in, Indicates the uniformity of crop height; represents the standard deviation of the UAV flight speed; represents the average flying speed of the drone; h represents the flying height of the drone during sowing; Indicates the optimal sowing flight height, as the preferred ; Step S304: Consider the impact of neighborhood effect on crops in adjacent grid cells, obtain neighborhood effect correction terms, and perform spatial coupling.

[0031] Taking variable fertilization of corn as an example, the influence of neighborhood effect on crops in adjacent grid cells is considered, and the neighborhood effect correction term is obtained for spatial coupling, which is specifically: The actual output is affected by the quality of the surrounding 3×3 grid operations; ;in, represents the corn yield after correction for neighborhood effects; represents the uncorrected corn yield; c represents the corn coverage rate within the field grid; Indicates the current grid corn coverage rate; represents the sum of corn coverage of the neighborhood grids, and nei represents the neighborhood identifier; in, ; ; Among them, A1 represents the grid position identifier; It represents the predicted value of corn yield at location A1; The average coverage of the 8 surrounding grids is 92%, and the current grid c self =95%; The corn yield after correction for neighborhood effect is: ; In step S400, the effect of the drone operation is quantified by comparing the crop growth data at different times, and the drone operation is automatically supervised according to the corresponding relationship between the drone operation trajectory data and the crop growth data, specifically: Step S401: taking the current crop growth data as a benchmark, collecting the crop growth data after a period of time, comparing the crop growth data at different times, and extracting the structural change index of the crop growth; Step S402: Automated supervision of the drone operation is performed based on the correspondence between the drone operation trajectory data and the crop growth data.

[0032] like Figure 3 The figure shows a visualization diagram of the dynamic growth curve and automated supervision of crops. The yield prediction at different times of each grid position is calculated according to the above method. In this embodiment, Δt=15 days. Time is used as the horizontal coordinate, and corn plant height and corn leaf area LAI are used as the vertical coordinates to display the stage changes of corn plant height and corn leaf area, and to predict and visualize the corn yield. For better display effect, the display curve can be scaled; in this embodiment, the corn leaf area LAI is 100 times magnified, that is, LAI (×100); the prediction of corn yield is the yield potential (%).

[0033] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for monitoring data of unmanned farm operations based on three-dimensional views, characterized in that: The unmanned farm operation data supervision method specifically includes the following steps: Step S100, collecting drone operation data and farm environment data; the drone operation data includes drone operation trajectory data and drone operation quality data; the farm environment data includes farm basic data, soil moisture data and crop growth data; Step S200: Based on the basic farm data, the drone operation trajectory data is superimposed to build a dynamic digital twin model of the farm, and the drone operation quality data, soil moisture data and crop growth data are displayed in real time; Step S300: analyzing the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; Step S400: quantify the effect of the drone operation by comparing the crop growth data at different times, and automatically supervise the drone operation according to the corresponding relationship between the drone operation trajectory data and the crop growth data.

2. According to claim 1, a method for monitoring data of unmanned farm operations based on three-dimensional views is characterized in that: In step S100, drone operation data and farm environment data are collected, specifically: The drone is equipped with a GPS positioning device, which obtains the location of the drone at certain time intervals to obtain the operation trajectory data of the drone; Obtaining basic farm data through satellite images, wherein the basic farm data includes the boundaries, areas and topographic data of different crops on the farm; The soil moisture data is obtained by deploying soil moisture sensors in a grid-like manner; Use drones to regularly capture multispectral images of crops and obtain crop growth data.

3. The method for monitoring data of unmanned farm operations based on three-dimensional views according to claim 2 is characterized in that: In step S200, the basic farm data is used as the basis, and the drone operation trajectory data is superimposed to build a farm dynamic digital twin model, which displays the drone operation quality data, soil moisture data and crop growth data in real time, specifically: Based on the time of collecting drone operation data and farm environment data, temporal and spatial alignment is performed; Display the boundaries, area and topographic data of different crops on the farm through a three-dimensional grid; The current UAV operation track is displayed and updated in real time through the GPS positioning device equipped on the UAV; Real-time display of drone operation quality data corresponding to the drone operation trajectory; Soil moisture data is indicated by color gradient; The crop growth curve over time is drawn through crop growth data for visual display.

4. The method for monitoring data of unmanned farm operations based on three-dimensional views according to claim 3 is characterized in that: In step S300, the corresponding relationship between the drone operation trajectory data and the crop growth data is analyzed according to the farm dynamic digital twin model, specifically: Step S301, dividing the farm into grid units of equal area, and recording the location, crop type and crop quantity of each unit; Step S302: According to the farm dynamic digital twin model, obtain the drone operation parameters O(x, y, t), and collect the crop growth data G(x, y, t+Δt) after a period of time Δt; wherein x and y represent the horizontal coordinate and vertical coordinate of the drone operation trajectory respectively; t represents the time mark of the acquisition; Step S303, obtaining several groups of the UAV operation parameters O(x, y, t) and crop growth data G(x, y, t+Δt) after a period of time Δt, performing data fitting, and obtaining estimation relationship functions between different crop growth data and the UAV operation parameters respectively; Step S304: Consider the impact of neighborhood effect on crops in adjacent grid cells, obtain neighborhood effect correction terms, and perform spatial coupling.

5. The method for monitoring data of unmanned farm operations based on three-dimensional views according to claim 4 is characterized in that: In step S400, the effect of the drone operation is quantified by comparing the crop growth data at different times, and the drone operation is automatically supervised according to the corresponding relationship between the drone operation trajectory data and the crop growth data, specifically: Step S401: taking the current crop growth data as a benchmark, collecting the crop growth data after a period of time, comparing the crop growth data at different times, and extracting the structural change index of the crop growth; Step S402: Automated supervision of the drone operation is performed based on the correspondence between the drone operation trajectory data and the crop growth data.

6. The method for monitoring data of unmanned farm operations based on three-dimensional views according to claim 5 is characterized in that: Specifically: Set timestamp; The timestamp is used to identify the time interval, obtain the continuous position data of the UAV, and obtain the operation trajectory of the UAV.

7. An unmanned farm operation data supervision system based on a three-dimensional view, applying an unmanned farm operation data supervision method based on a three-dimensional view as claimed in any one of claims 1 to 6, characterized in that: The unmanned farm operation data supervision system includes a data acquisition module, a data processing module, a digital twin modeling module, a data analysis module and a data supervision and visualization module; The data acquisition module is used to collect drone operation data and farm environment data; The data processing module is used to align the timestamps of the collected UAV operation data with the farm environment data to provide continuous data; The digital twin modeling module is used to build a dynamic digital twin model of the farm based on the basic farm data and superimpose the drone operation trajectory data, and to display the drone operation quality data, soil moisture data and crop growth data in real time; The data analysis module is used to analyze the correspondence between the drone operation trajectory data and the crop growth data according to the farm dynamic digital twin model; The data supervision and visualization module is used to compare crop growth data at different times, quantify the effect of drone operations, automatically supervise drone operations based on the correspondence between the drone operation trajectory data and crop growth data, and visualize the growth curve of crops over time.

8. The unmanned farm operation data monitoring system based on three-dimensional view according to claim 7 is characterized by: The data acquisition module includes a drone operation data unit, a farm environment data unit and a data transmission unit; The drone operation data unit is used to obtain drone operation data, and the drone operation data includes drone operation trajectory data and drone operation quality data; The farm environment data unit is used to obtain farm environment data, and the farm environment data includes basic farm data, soil moisture data and crop growth data; The data transmission unit is used for long-distance data transmission via LoRaWAN.

9. The unmanned farm operation data monitoring system based on three-dimensional view according to claim 8 is characterized by: Specifically: Back up the collected drone operation data, farm environment data and crop growth curves over time; The crop growth curve over time supports playback.

Images