Sweet potato growth parameter monitoring method based on unmanned aerial vehicle multispectral remote sensing

Abstract

The invention discloses a sweet potato growth parameter monitoring method based on unmanned aerial vehicle multispectral remote sensing. The method comprises the following steps: S1, establishing a monitoring system for monitoring sweet potato growth; s2, collecting physiological parameters of the sweet potatoes by using a multispectral remote sensor of the unmanned aerial vehicle; s3, converting the physiological parameters into growth state data by the monitoring system; s4, the monitoring system transversely compares the growth state data of a plurality of time periods of the same day, calculates a rising value of the growth state data, and records the rising value; s5, the monitoring system summarizes growth state data of different time periods of the day according to the number of days, transversely compares the growth state data of the number of days in a week with the week as a time period, and records the data; and S6, calculating a rising value displayed by a comparison result of the growth state data of the sweet potatoes in each current week and the growth state data of the sweet potatoes in the last week, and combining the rising value to obtain complete growth parameters. According to the invention, the growth parameters of the large-scale sweet potato planting field can be visually monitored.

Description

Technical Field

[0001] The invention belongs to the technical field of unmanned aerial vehicle remote sensing, and in particular relates to a sweet potato growth parameter monitoring method based on unmanned aerial vehicle multispectral remote sensing. Background Art

[0002] Sweet potato is a vine plant whose stems spread and crawl on the ground. The roots are the main edible part. They are usually block-shaped or long, and sometimes come in different colors, such as orange, purple or white. Research on sweet potato variety selection and high-yield cultivation is still limited to the stage of manual fixed-point sampling, and then data is summarized to determine the growth of purple sweet potatoes.

[0003] In order to solve this problem, the purple sweet potato growth monitoring system of China Utility Model Patent (authorization announcement number is CN203299643U) uses the real-time soil temperature and humidity conditions during the growth period of purple sweet potatoes by burying multiple temperature sensors and humidity sensors in the soil where purple sweet potatoes are planted. At the same time, it cooperates with the light intensity detector, soil analyzer and soil fertilizer rapid tester to detect the light intensity, the content of various elements in the soil and the fertilizer content, so as to monitor the entire growth process of purple sweet potatoes.

[0004] Although the aforementioned technical solution monitors the sweet potato through temperature sensors and humidity sensors to monitor its growth process, this mode is only suitable for observation in the laboratory. The cost of using sensors and light meters to monitor large-scale sweet potato cultivation is extremely high and cannot be realized at all. At the same time, the aforementioned technical solution can only monitor the growth of sweet potatoes and cannot visualize the sweet potato growth data. Summary of the invention

[0005] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and to provide a sweet potato growth parameter monitoring method based on unmanned aerial vehicle multispectral remote sensing. The multispectral remote sensor can obtain surface information with high resolution and capture tiny changes in the sweet potato growth process, thereby more accurately evaluating the growth status of the sweet potato and the health of the vegetation.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for monitoring sweet potato growth parameters based on unmanned aerial vehicle multispectral remote sensing, comprising the following steps:

[0008] S1. Establish a monitoring system for monitoring sweet potato growth and connect drones equipped with multispectral remote sensors to the monitoring system;

[0009] S2, the monitoring system instructs the UAV to fly around the target sweet potato field at set intervals T, and uses the multispectral remote sensor of the UAV to collect the physiological parameters of the sweet potato;

[0010] S3, uploading the collected sweet potato physiological parameters to the monitoring system, and the monitoring system converts the physiological parameters into growth status data;

[0011] S4, the monitoring system compares the growth status data of multiple time periods on the day horizontally, calculates the rising value of the growth status data, and records the rising value;

[0012] S5. The monitoring system summarizes the growth status data of different time periods of the day by day, compares the growth status data of days in the week horizontally by week as the time period, and records them;

[0013] S6. Calculate the increase value shown by the comparison of the sweet potato growth status data of the current week and the previous week, using the formula ΔP i =P i (t)-P i (t-1) represents the parameter P i The change in a time period t, where P i (t) is the parameter value of the current time period, P i (t-1) is the parameter value of the previous time period; if ΔP i >0, it means that the parameter has increased during this period, that is, there is an "ascending" stage, and combined with the rising value, the complete growth parameter is obtained.

[0014] As a preferred technical solution, the monitoring system includes: a data transmission layer, a data processing layer, a data integration and analysis layer, a visualization display layer and a decision support layer;

[0015] The data transmission layer is used to receive data collected by the multispectral remote sensor of the UAV;

[0016] The data processing layer includes a preprocessing module, a feature extraction module and a feature selection module. The preprocessing module is used to clean the collected data, remove abnormal values ​​and fill missing values ​​to ensure the quality and accuracy of the data; the feature extraction module is used to extract statistical features from physiological parameter data and extract gradient values ​​from surface temperature data; the feature selection module is used to screen and select features that have an important impact on the growth state of sweet potatoes to improve the accuracy and generalization ability of the model;

[0017] The data integration and analysis layer includes a data integration module, a database management system, and a data analysis algorithm. The data integration module is used to integrate the data acquired by the multispectral remote sensor with the meteorological data and the soil moisture data; the database management system is used to store and manage all collected and processed data, and supports fast query and efficient data retrieval; the data analysis algorithm applies machine learning to identify patterns and trends in the data to help evaluate the growth status of sweet potatoes;

[0018] The visualization display layer includes a graphical user interface, a Web service or a mobile application. The graphical user interface provides an intuitive operation interface for users, and displays charts and curves showing changes in various parameters during the growth of sweet potatoes. The Web service or mobile application enables users to access the latest sweet potato growth information through the Internet or mobile devices to achieve remote monitoring.

[0019] The decision support layer includes an anomaly detection and alarm system and a planting management strategy. The anomaly detection and alarm system is used to automatically detect abnormal conditions during the growth of sweet potatoes and issue an alarm in a timely manner; the planting management strategy provides suggestions for optimizing the planting management strategy based on the analysis results.

[0020] As a preferred technical solution, in step S1, the drone is connected to the monitoring system by wireless means, specifically:

[0021] S11. Use LoRaWAN as the communication protocol to enable effective data transmission between the monitoring system and the drone;

[0022] S12, installing the multispectral remote sensor on the drone, and connecting the drone to the monitoring system using the LoRaWAN communication protocol;

[0023] S13, installing a MATLAB software program in the monitoring system for receiving, parsing and processing data from the multispectral remote sensor;

[0024] S14. Integrate the vegetation index, surface temperature, leaf area index, chromaticity index and soil moisture data obtained by the multispectral remote sensor with other data in the monitoring system for comprehensive analysis and processing;

[0025] S15. After connection, perform system testing and verification on the monitoring system and the drone.

[0026] As a preferred technical solution, in step S2, the UAV flight route is planned according to the geographical location and scope of the target sweet potato field, using map software ArcGIS or QGIS to design the flight path of the UAV. The UAV's flight altitude during the patrol flight is 1 / 50m of the sweet potato field area value, and the flight speed is 1-3m per second.

[0027] As a preferred technical solution, in step S2, the UAV flight route design includes the following steps:

[0028] S21. Draw the boundary of the sweet potato field in a map software according to the geographical location and range of the sweet potato field;

[0029] S2.2, starting from the starting point, start flying along the boundary of the sweet potato field, and maintain the flight altitude at 1 / 50 meter of the sweet potato field area;

[0030] S2.3, set the drone to turn once every certain distance based on its field of view to ensure that the flight path covers the entire sweet potato field area;

[0031] S2.4. Control the flight speed of the drone to 1-3 meters per second to ensure that sufficient data can be collected during the flight.

[0032] As a preferred technical solution, in steps S2 and S3, the sweet potato physiological parameters include vegetation index, surface temperature, leaf area index, chromaticity index and soil moisture, and the vegetation index also includes NDVI and NDRE. The NDVI is an index for measuring the degree of vegetation coverage, and the NDRE is an index for evaluating the health of vegetation through the ratio of the near-infrared band and the red edge band.

[0033] As a preferred technical solution, the growth status data in step S3 includes: growth rate, growth stage, leaf area index, leaf chromaticity, leaf area and leaf chlorophyll content.

[0034] As a preferred technical solution, in step 3, the monitoring system converts the physiological parameters into growth status data, specifically:

[0035] S31. Data collection: Data collected by drones using multispectral remote sensors, including vegetation indices NDVI and NDRE, surface temperature, leaf area index, chromaticity index, and soil moisture;

[0036] S32. Data preprocessing: The collected data needs to be preprocessed, including data cleaning, removing outliers, and filling missing values ​​to ensure the quality and accuracy of the data;

[0037] S33, feature extraction: extract features from physiological parameter data, extract mean, maximum, and variance statistical features from NDVI, and extract gradient from surface temperature data;

[0038] S34. Feature selection: Screen and select the extracted features, retain the features that have an important impact on the growth status of sweet potatoes, and remove redundant or irrelevant features to improve the accuracy and generalization ability of the model.

[0039] As a preferred technical solution, step 4 also includes data collection and collation, and the data collection and collation formula is:

[0040] D {t} ={d {t1} ,d {t2} ,…,d {tn}}

[0041] Where D {t} Represents a collection of growth status data at different time periods of the day;

[0042] {t} represents the index of the time period;

[0043] The formula for horizontal comparison of data is:

[0044] Δp {t} =p {t2} -p {t1}

[0045] Where p represents each growth state parameter;

[0046] p {ti} Represents the i-th parameter data in time period t

[0047] Δp {t} It represents the change of parameter p in time period t.

[0048] As a preferred technical solution, the step S4 further includes rising value calculation, and the rising value calculation includes the following formula:

[0049]

[0050] where Δp {t} >0 means that parameter p increases in time period t;

[0051] N represents the total number of time periods on the day.

[0052] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0053] 1. The present invention uses drones to cover a wide range of sweet potato planting areas in a short time, and the multispectral remote sensor can obtain surface information with high resolution and capture tiny changes in the growth process of sweet potatoes, thereby more accurately evaluating the growth status of sweet potatoes and the health of vegetation. By collecting multiple physiological parameters such as vegetation index (such as NDVI, NDRE), surface temperature, leaf area index, chromaticity index and soil moisture, the system can fully understand the growth status of sweet potato planting areas, achieving the beneficial effect of being able to monitor large-scale sweet potato planting areas.

[0054] 2. The present invention integrates the data acquired by the multispectral remote sensor with other data through the monitoring system for comprehensive analysis and processing. By integrating different data together, combining with the database management system and performing graphical user interface visualization, the monitoring system compares the growth status data of different time periods horizontally, summarizes them by week, and compares the growth status data of different days of the week horizontally, quickly discovers abnormal conditions or periodic changes, and thus adjusts the planting management strategy in time. By regularly collecting, uploading and processing sweet potato growth parameter data, a visualization chart or curve of the sweet potato growth status is generated in real time, and the changing trend of various parameters in the sweet potato growth process is intuitively displayed, such as vegetation index, surface temperature, and leaf area index, achieving the beneficial effect of visualizing the monitoring of sweet potato growth data. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. 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 creative work.

[0056] Figure 1 This is a flow chart of a method for monitoring sweet potato growth parameters based on multispectral remote sensing of unmanned aerial vehicles according to an embodiment of the present invention;

[0057] Figure 2 It is a schematic diagram of the structure of the monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0059] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0060] like Figure 1As shown, this embodiment provides a method for monitoring sweet potato growth parameters based on drone multispectral remote sensing, comprising the following steps:

[0061] S1. Establish a monitoring system for monitoring sweet potato growth and connect drones equipped with multispectral remote sensors to the monitoring system.

[0062] like Figure 2 As shown, the monitoring system of this embodiment includes a data transmission layer, a data processing layer, a data integration and analysis layer, a visualization display layer and a decision support layer, which are as follows:

[0063] Data transmission layer;

[0064] Wireless connection: The drone is connected to the monitoring system wirelessly to ensure real-time data upload.

[0065] MATLAB software program: installed in the monitoring system to receive, analyze and process data from the multispectral remote sensor.

[0066] Data processing layer;

[0067] Preprocessing module: responsible for cleaning the collected data, removing outliers, and filling missing values ​​to ensure the quality and accuracy of the data.

[0068] Feature extraction module: extracts statistical features (such as mean, maximum, variance) from physiological parameter data, and extracts gradient from surface temperature data.

[0069] Feature selection module: Screen and select features that have an important impact on the growth status of sweet potatoes to improve the accuracy and generalization ability of the model.

[0070] Data integration and analysis layer;

[0071] Data integration module: Integrate the data acquired by the multispectral remote sensor with other related data (such as meteorological data, soil moisture data, etc.) for comprehensive analysis.

[0072] Database Management System: used to store and manage all collected and processed data, supporting fast query and efficient data retrieval.

[0073] Data analysis algorithms: Apply machine learning or other advanced analytical techniques to identify patterns and trends in the data to help assess sweet potato growth conditions.

[0074] Visual display layer;

[0075] Graphical User Interface (GUI): Provides an intuitive operating interface for users, allowing them to easily view the generated charts and curves and understand the changing trends of various parameters during the growth of sweet potatoes.

[0076] Web service or mobile application: enables users to access the latest sweet potato growth information through the Internet or mobile devices for remote monitoring.

[0077] Decision support layer;

[0078] Abnormal detection and alarm system: automatically detects abnormal conditions during the growth of sweet potatoes and issues alarms in time to remind managers to take necessary measures.

[0079] Planting management strategy: Provide recommendations for optimizing planting management strategies based on the analysis results, such as irrigation and fertilization, to promote the healthy growth of sweet potatoes.

[0080] Furthermore, the monitoring system is wirelessly connected to the drone, and the specific steps are as follows:

[0081] S11. Use LoRaWAN as the communication protocol to enable effective data transmission between the monitoring system and the drone;

[0082] S12, installing the multispectral remote sensor on the drone and connecting it to the monitoring system, also using the LoRaWAN communication protocol;

[0083] S13, installing a MATLAB software program in the monitoring system for receiving, parsing and processing data from the multispectral remote sensor;

[0084] S14. Integrate the data acquired by the multispectral remote sensor with other data in the monitoring system for comprehensive analysis and processing;

[0085] S15. After the implementation is completed, the monitoring system and drone are systematically tested and verified.

[0086] Through system testing and verification, the effectiveness of the LoRaWAN communication protocol between the monitoring system and the drone is verified, including checking the stability of communication, the accuracy of data transmission, and the communication distance, ensuring that the communication system can operate reliably under various environmental conditions. Through system testing and verification, the hardware connection between the multispectral remote sensor and the drone and monitoring system is stable and reliable.

[0087] S2. The monitoring system instructs the UAV to fly around the target sweet potato field every 6h-12h and use multi-spectral remote sensors to collect sweet potato physiological parameters.

[0088] Furthermore, in step S2, the UAV flight route is planned according to the geographical location and scope of the target sweet potato field, using map software ArcGIS or QGIS to design the flight path of the UAV. When the UAV patrols, the flight altitude is 1 / 50 (m) of the sweet potato field area and the flight speed is 1-3m per second.

[0089] By using mapping software to design the flight path, we ensure that the drone can completely cover the geographical scope of the target sweet potato field and that the remote sensing data obtained covers information on the entire sweet potato planting area, which helps to comprehensively monitor the growth status of the sweet potato.

[0090] Furthermore, the UAV flight route design includes the following steps:

[0091] S21. Draw the boundary of the sweet potato field in a map software according to the geographical location and range of the sweet potato field;

[0092] S22, starting from the starting point, starting to fly along the border of the sweet potato field, maintaining the flight altitude at 1 / 50 meter of the area of ​​the sweet potato field;

[0093] S23, setting a certain distance to determine a turn based on the field of view of the drone to ensure that the flight path covers the entire sweet potato field area;

[0094] S24. Control the flight speed of the drone to 1-3 meters per second to ensure that sufficient data can be collected during the flight.

[0095] It can be understood that this embodiment ensures that the UAV can completely and accurately cover the geographical scope of the target sweet potato field by drawing the boundaries of the sweet potato field in the map software and flying along these boundaries. The flight altitude is 1 / 50 meter of the sweet potato field area, which helps to ensure that the UAV can obtain ground data at the optimal altitude during the flight. The flight speed is set to 1-3 meters per second to ensure that the UAV can fully and evenly collect data from the sweet potato field during the flight.

[0096] S3. The regularly collected sweet potato physiological parameters are uploaded to the monitoring system, which converts the physiological parameters into growth status data.

[0097] Specifically, the sweet potato physiological parameters in step S3 include vegetation index, surface temperature, leaf area index, chromaticity index and soil moisture. The vegetation index also includes NDVI and NDRE. NDVI (Normalized Difference Vegetation Index) is an index for measuring the degree of vegetation coverage, and NDRE (Normalized Difference Red Edge) is an index for evaluating the health of vegetation through the ratio of the near-infrared band and the red edge band.

[0098] Specifically, the growth status data in step S3 include: growth rate, growth stage, leaf area index, leaf chromaticity, leaf area and leaf chlorophyll content.

[0099] Furthermore, step S3 of converting physiological parameters into growth status data further includes the following steps:

[0100] S3.1. Data collection: Data collected by drones using multispectral remote sensors, including vegetation indices NDVI and NDRE, surface temperature, leaf area index, chromaticity index, and soil moisture;

[0101] S32. Data preprocessing: The collected data needs to be preprocessed, including data cleaning, removing outliers, and filling missing values ​​to ensure the quality and accuracy of the data;

[0102] S33, feature extraction: extract features from physiological parameter data, extract statistical features such as mean, maximum, variance from NDVI, and extract gradient from surface temperature data;

[0103] S34. Feature selection: Screen and select the extracted features, retain the features that have an important impact on the growth status of sweet potatoes, and remove redundant or irrelevant features to improve the accuracy and generalization ability of the model.

[0104] S4. The monitoring system compares the growth status data of multiple time periods on the same day horizontally, calculates the rising value in the growth status data, and records the data.

[0105] Specifically, step S4 also includes data collection and collation, and the data collection and collation formula is:

[0106] D {t} ={d {t1} ,d {t2} ,…,d {tn}}

[0107] Where D {t} Represents a collection of growth status data at different time periods of the day;

[0108] {t} represents the index of the time period.

[0109] Specifically, the data horizontal comparison formula in step S4 is:

[0110] Δp {t} =p {t2} -p {t1}

[0111] Where p represents each growth state parameter;

[0112] p {ti} Represents the i-th parameter data in time period t

[0113] Δp {t} It represents the change of parameter p in time period t.

[0114] By using the form of data sets, the growth status data of different time periods are organized into a clear set to facilitate subsequent data analysis and processing. The time period index is used so that the data of different time periods can be intuitively compared and contrasted, which helps to observe the changing trend of growth status over time.

[0115] Specifically, step S4 also includes rising value calculation, and the rising value calculation includes the following formula:

[0116]

[0117] where Δp {t} >0 means that parameter p increases in time period t;

[0118] N represents the total number of time periods on the day.

[0119] By calculating the rising values ​​of parameters in different time periods, the changing trend of growth state can be quantitatively described. In the formula, Δp {t} >0 means that the parameter increases in time period t. Therefore, this formula highlights the positive changes in the growth status, allowing the monitoring system to quickly identify the positive changes in the growth status of sweet potatoes and take corresponding management measures in a timely manner. The calculation results of the rising value are intuitive and clear, and can quickly determine the changing trend of the growth status of sweet potatoes.

[0120] S5. The monitoring system summarizes the growth status data of different time periods of the day by day, compares the growth status data of days in the week horizontally by week as the time period, and records them;

[0121] S6. Calculate the rising value shown by the comparison result of the sweet potato growth status data of the current week and the previous week, and combine the rising data recorded in step S4 to obtain the complete growth parameters.

[0122] Step S6 specifically includes using the formula ΔP i =P i (t)-P i (t-1) represents the parameter P i The change in a time period t, where P i (t) is the parameter value of the current time period, P i (t-1) is the parameter value of the previous time period; if ΔP i >0, it means that the parameter has increased during this period, that is, there is an "ascending" stage, and combined with the rising value, the complete growth parameter is obtained.

[0123] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0124] The technical features of the above embodiments may 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.

[0125] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A method for monitoring sweet potato growth parameters based on multispectral remote sensing using unmanned aerial vehicles, characterized in that: The steps include: S1. Establish a monitoring system for monitoring sweet potato growth and connect drones equipped with multispectral remote sensors to the monitoring system; S2, the monitoring system instructs the UAV to fly around the target sweet potato field at set intervals T, and uses the multispectral remote sensor of the UAV to collect the physiological parameters of the sweet potato; S3, uploading the collected sweet potato physiological parameters to the monitoring system, and the monitoring system converts the physiological parameters into growth status data; S4, the monitoring system compares the growth status data of multiple time periods on the day horizontally, calculates the rising value of the growth status data, and records the rising value; S5. The monitoring system summarizes the growth status data of different time periods of the day by day, compares the growth status data of days in the week horizontally with the week as the time period, and records them; S6. Calculate the increase value shown by the comparison of the sweet potato growth status data of the current week and the previous week, using the formula ΔP i =P i (t)-P i (t-1) represents the parameter P i The change in a time period t, where P i (t) is the parameter value of the current time period, P i (t-1) is the parameter value of the previous time period; if ΔP i >0, it means that the parameter has increased during this period, that is, there is an "upward" stage, and combined with the upward value, the complete growth parameter is obtained.

2. The sweet potato growth parameter monitoring method based on unmanned aerial vehicle multispectral remote sensing according to claim 1, characterized in that: The monitoring system includes: a data transmission layer, a data processing layer, a data integration and analysis layer, a visualization display layer and a decision support layer; The data transmission layer is used to receive data collected by the multispectral remote sensor of the UAV; The data processing layer includes a preprocessing module, a feature extraction module and a feature selection module. The preprocessing module is used to clean the collected data, remove abnormal values ​​and fill missing values ​​to ensure the quality and accuracy of the data; the feature extraction module is used to extract statistical features from physiological parameter data and extract gradient values ​​from surface temperature data; the feature selection module is used to screen and select features that have an important impact on the growth state of sweet potatoes to improve the accuracy and generalization ability of the model; The data integration and analysis layer includes a data integration module, a database management system, and a data analysis algorithm. The data integration module is used to integrate the data acquired by the multispectral remote sensor with the meteorological data and the soil moisture data; the database management system is used to store and manage all collected and processed data, and supports fast query and efficient data retrieval; the data analysis algorithm applies machine learning to identify patterns and trends in the data to help evaluate the growth status of sweet potatoes; The visualization display layer includes a graphical user interface, a Web service or a mobile application. The graphical user interface provides an intuitive operation interface for users, and displays charts and curves showing changes in various parameters during the growth of sweet potatoes. The Web service or mobile application enables users to access the latest sweet potato growth information through the Internet or mobile devices to achieve remote monitoring. The decision support layer includes an anomaly detection and alarm system and a planting management strategy. The anomaly detection and alarm system is used to automatically detect abnormal conditions during the growth of sweet potatoes and issue an alarm in a timely manner; the planting management strategy provides suggestions for optimizing the planting management strategy based on the analysis results.

3. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 1, characterized in that: In step S1, the drone is connected to the monitoring system by wireless means, specifically: S11. Use LoRaWAN as the communication protocol to enable effective data transmission between the monitoring system and the drone; S12, installing the multispectral remote sensor on the drone, and connecting the drone to the monitoring system using the LoRaWAN communication protocol; S13, installing a MATLAB software program in the monitoring system for receiving, parsing and processing data from the multispectral remote sensor; S14. Integrate the vegetation index, surface temperature, leaf area index, chromaticity index and soil moisture data obtained by the multispectral remote sensor with other data in the monitoring system for comprehensive analysis and processing; S15. After connection, perform system testing and verification on the monitoring system and the drone.

4. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 1, characterized in that: In step S2, the UAV flight route is planned according to the geographical location and scope of the target sweet potato field, using map software ArcGIS or QGIS to design the flight path of the UAV. The UAV flies at a flight altitude of 1 / 50m of the area of ​​the sweet potato field and a flight speed of 1-3m per second.

5. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 4, characterized in that: In step S2, the UAV flight route design includes the following steps: S21. Draw the boundary of the sweet potato field in a map software according to the geographical location and range of the sweet potato field; S2.2, starting from the starting point, start flying along the boundary of the sweet potato field, and maintain the flight altitude at 1 / 50 meter of the sweet potato field area; S2.3, set the drone to turn once every certain distance based on its field of view to ensure that the flight path covers the entire sweet potato field area; S2.

4. Control the flight speed of the drone to 1-3 meters per second to ensure that sufficient data can be collected during the flight.

6. The method for monitoring sweet potato growth parameters based on unmanned aerial vehicle multispectral remote sensing according to claim 1, characterized in that: In steps S2 and S3, the sweet potato physiological parameters include vegetation index, surface temperature, leaf area index, chromaticity index and soil moisture. The vegetation index also includes NDVI and NDRE. The NDVI is an index for measuring the degree of vegetation coverage, and the NDRE is an index for evaluating the health status of vegetation through the ratio of the near-infrared band and the red edge band.

7. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 1, characterized in that: The growth status data in step S3 include: growth rate, growth stage, leaf area index, leaf chromaticity, leaf area and leaf chlorophyll content.

8. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 7, characterized in that: In step 3, the monitoring system converts the physiological parameters into growth status data, specifically: S31. Data collection: Data collected by drones using multispectral remote sensors, including vegetation indices NDVI and NDRE, surface temperature, leaf area index, chromaticity index, and soil moisture; S32. Data preprocessing: The collected data needs to be preprocessed, including data cleaning, removing outliers, and filling missing values ​​to ensure the quality and accuracy of the data; S33, feature extraction: extract features from physiological parameter data, extract mean, maximum, and variance statistical features from NDVI, and extract gradient from surface temperature data; S34. Feature selection: Screen and select the extracted features, retain the features that have an important impact on the growth status of sweet potatoes, and remove redundant or irrelevant features to improve the accuracy and generalization ability of the model.

9. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 1, characterized in that: The step 4 also includes data collection and collation, and the data collection and collation formula is: D {t} ={d {t1} ,d {t2} ,…,d {tn} } Where D {t} Represents a collection of growth status data at different time periods of the day; {t} represents the index of the time period; The formula for horizontal comparison of data is: Δp {t} =p {t2} -p {t1} Where p represents each growth state parameter; p {ti} Represents the i-th parameter data in time period t Δp {t} It represents the change of parameter p in time period t.

10. The method for monitoring sweet potato growth parameters based on multispectral remote sensing by unmanned aerial vehicle according to claim 1, characterized in that: The step S4 further includes a rising value calculation, and the rising value calculation includes the following formula: Where Δp {t} >0 means that parameter p increases in time period t; N represents the total number of time periods on the day.

Images