Open access peer-reviewed chapter
Key equations governing of remote sensing mechanisms in agricultural.
Abstract
This chapter explores the future trends and advancements of Agricultural Unmanned Aerial Vehicles (Ag-UAVs), highlighting their revolutionary impact on modern agriculture. The discussion is organized into five key sections. Firstly, it examines fundamental principles and emerging trends, focusing on innovations in remote sensing mechanisms, including the use of electromagnetic spectrum analysis and vegetation indices (VIs). Secondly, it delves into the principles and applications of advanced technologies, such as high-resolution, multispectral imaging, Light Detection and Ranging (LiDAR), and thermal sensors, which enable precision tasks like targeted fertilizer and pesticide applications. The third section investigates essential components and recent advancements in Ag-UAVs, such as global positioning systems (GPS) modules, flight control systems, autonomous operating systems, and real-time mission tools, which optimize their performance for precision farming. The fourth section addresses the innovative applications of Ag-UAVs in crop monitoring, health assessment, and yield prediction, emphasizing their role in managing and optimizing agricultural practices. Finally, the integration of Artificial Intelligence (AI) enhances the capabilities of Ag-UAVs, enabling advanced data analysis for crop health assessment, pest detection, and growth monitoring. AI-driven precision operations and yield predictions further support farming by transforming traditional methods into efficient, data-driven ecosystems. In conclusion, the adoption of Ag-UAVs, coupled with advanced technologies such as AI and multispectral imaging.
Keywords
- agricultural unmanned aerial vehicles (Ag-UAVs)
- vegetation index (Vis)
- temperature-vegetation dryness index (TVDI)
- crop health assessment
- field crop monitoring
1. Introduction
Agricultural Unmanned Aerial Vehicles (Ag-UAVs) have become pivotal in transforming conventional agriculture into smart agriculture. These advancements integrate remote sensing technology, global positioning systems (GPS), artificial intelligence (AI), and the Internet of Things (IoT) to enhance the functionality and utility of Ag-UAVs. By leveraging these technologies, Ag-UAVs have emerged as essential tools for modern farmers engaged in smart farm management [1].
Key applications include sensor-based monitoring of vegetation indices, data analysis from high-resolution aerial imagery, and navigation systems equipped with imaging and sensory technologies, as shown in Figure 1(a). Ag-UAVs provide farmers with in-depth, actionable insights, such as creating detailed 2D and 3D agricultural maps [2, 3]. These models support strategic planning for farm management, enabling the monitoring of crop health, growth patterns, and yield forecasting. Furthermore, Ag-UAVs play a critical role in assessing soil quality and improving overall productivity while simultaneously reducing waste. By enabling real-time communication and data-driven decision-making, Ag-UAVs empower farmers to enhance operational efficiency and achieve precise resource allocation. Specialized software further weed in the efficient collection and analysis of critical farm data, supporting rapid and accurate decision-making processes [4]. Modern Ag-UAVs also facilitate automation in various smart farming tasks, such as precision and autonomous spraying of pesticides, fertilizers, and growth stimulants [5], as shown in Figure 1(b). The integration of AI enhances data processing capabilities, enabling predictive analytics for yield estimation and real-time farm management [6]. Despite these advances, challenges such as regulatory constraints, limited battery life, and payload capacity remain barriers to widespread adoption, as shown in Figure 1.
Figure 1.
Ag-UAVs are transforming farming operations: (a) High-resolution aerial imagery, multispectral and thermal imaging, (b) Innovations also facilitate tasks like targeted application of autonomous spray fertilizers and pesticides.
Nonetheless, the integration of remote sensing, GPS technology, AI, and IoT within Ag-UAV systems demonstrates significant potential for more efficient resource allocation and environmental management. These innovations pave the way toward a sustainable and efficient future for smart farming, addressing both current and emerging agricultural challenges [7]. These innovations also facilitate tasks like targeted application of fertilizers and pesticides, minimizing chemical usage, and ensuring uniform coverage as shown in Figure 1(b). Despite their transformative potential, Ag-UAVs face challenges such as regulatory barriers, high initial costs, and the need for skilled operators [5]. Limitations in battery capacity and payload also present constraints. However, continuous technological developments, including AI integration and IoT connectivity, are improving real-time data analysis and enhancing overall farm management [8]. These systems are not only driving efficiency but are also supporting sustainable practices by optimizing resources and reducing environmental impact. As costs decline and regulations adapt, Ag-UAVs are becoming increasingly accessible, benefiting farms of all sizes and shaping the future of agriculture as shown in Figure 1.
2. Basic principles and key future trends of Ag-UAVs in recent advances, innovations and applications
2.1 Basic principles of the electromagnetic spectrum of remote sensing mechanisms in agriculture
The electromagnetic spectrum includes a range of wavelengths that are essential for modern agricultural practices, especially when applied through Ag-UAVs. These Ag-UAVs are equipped with sophisticated sensors and imaging systems, allowing them to collect detailed data that helps identify issues such as crop diseases, irrigation inefficiencies, and nutrient deficiencies [9]. The use of specific spectral bands improves real-time monitoring of crop conditions and livestock activity, enhancing precision and efficiency in farm management. Ag-UAVs are particularly effective in the precision spraying of water and agrochemicals, utilizing environmental data to ensure targeted and efficient application [10]. This process reduces waste and supports sustainable practices. A critical aspect of their functionality involves leveraging specific parts of the electromagnetic spectrum, as shown in Figure 2. Key bands, such as Near-Infrared (NIR), Red Edge, and thermal wavelengths, are highly effective in evaluating vegetation health by analyzing indicators like chlorophyll levels [11], as shown in Figure 3(a). Additionally commonly used wavelengths range from 300 nm to 2500 nm, capturing the effects of solar radiation [12] as shows in Figure 3(b) optical radiation in agriculture operates across a wide range from 100 to 1 mm, with each wavelength offering unique insights into various agricultural parameters. These advanced capabilities make Ag-UAVs indispensable tools in precision agriculture, supporting sustainable and data-driven farm operations as shown in Figure 3.
Figure 2.
A critical aspect of their functionality involves leveraging specific parts of the electromagnetic spectrum.
Figure 3.
Key bands, such as NIR, red edge, and thermal wavelengths, are highly effective in evaluating vegetation health: (a) the effects of solar radiation on cell structure and (b) analyzing indicators like chlorophyll levels.
2.2 Vegetation indices (VIs)
In the domain of Ag-UAVs and remote sensing, VIs play a crucial role in analyzing and interpreting various agricultural features [13]. They are instrumental in monitoring crop growth, distinguishing vegetation from non-vegetation areas, and providing detailed information on soil conditions and other related parameters [3]. VIs is particularly valuable for assessing plant health, vigor, and stress levels, enabling precise evaluations through Ag UAVs based remote sensing systems as shown in Figure 3. These indices assist in tracking vegetation coverage, biomass, and other agronomic metrics critical for effective farm management [14]. Among the commonly utilized vegetation indices are the Normalized Difference Vegetation Index (NDVI), the Soil-Adjusted Vegetation Index (SAVI), the Enhanced Vegetation Index (EVI), the Normalized Difference Red Edge Index (NDRE or RedNDVI), and the Tensor Structure Variation Index (TSVI), as shown in Table 1. Each index offers unique insights and applications in agriculture, helping optimize resource use and improve productivity when integrated with UAV technologies.
| Index | Bands | Eq. | Ref. |
|---|---|---|---|
| Normalized Difference Vegetation Index (NDVI) | NIR/Red Edge | NDVI = (NIR − R)/NIR + R) | [15, 16, 17, 18] |
| Green Normalized Difference Vegetation (GNDVI) | G/NIR, Red Edge | GNDVI = (NIR − Green)/(NIR + Green) | [15] |
| Red Edge Index (NDRE or RedNDVI)/Effects of the spectral response functions of sensors on VIs | NIR, Red Edge | [13] | |
| The enhanced vegetation index (EVI) | G/NIR, Red Edge | [18] | |
| Soil-adjusted vegetation index (SAVI) | NIR/Red Edge | [18, 19] | |
| Tensor Structure Variation Index (TSVI) | NIR/Red Edge | [16, 20] | |
| [18] | |||
| Optimized Soil-Adjusted Vegetation Index (OSAVI): | G/NIR, Red Edge | [21] |
Table 1.
2.2.1 Role of VIs in Ag-UAVs-based agricultural monitoring
VIs derived from remote sensing data play a critical role in enhancing the capabilities of agricultural UAVs. These indices offer valuable insights into crop health, detect stress, and monitor variability across fields, enabling precise and large-scale vegetation analysis [3]. This is vital for improving productivity, identifying diseases, managing water stress, and optimizing overall farming practices [22]. Among commonly used VIs, the NDVI is particularly effective for general assessments of crop health due to its simplicity and reliability. The SAVI is advantageous in areas with sparse vegetation or where soil interference is significant, while EVI is better suited for high-biomass environments, offering enhanced sensitivity to subtle variations in dense vegetation [23] in Table 1.
2.2.2 Use of VIs in Ag-UAVs applications
Ag-UAVs equipped with multispectral or hyperspectral sensors are capable of capturing reflectance data across a range of wavelengths, such as R, G, B, NIR, and SAVI [18]. These reflectance values are used to compute vegetation indices like NDVI, GNDVI, RedNDVI, EVI, SAVI, and TSAVI in Table 1 by analyzing these indices [21]. Ag-UAVs provide valuable insights into crop health, detect stress, and assess variability across fields [6], as shown in Figure 3. This data supports effective decision-making for managing crops and optimizing yields. VIs is calculated using specific mathematical Eq. (1) tailored to these applications, enabling precision agriculture practices and the development of advanced technology is the key to rapid and non-destructive detection [24] as in Eq. (1):
Where:
Figure 4.
Ag-UAVs are equipped with high-resolution cameras and advanced sensors: (a) Multispectral cameras, (b) Smart controllers, (c) Flight Control Systems (FCS) and autonomous systems in Ag-UAVs, (d) Multispectral imaging, (e) High-resolution imaging of RGB cameras, and (f) NDVI imaging.
3. Principles of advantage technology in future and trends for Ag-UAVs
Developments in Ag-UAV applications are revolutionizing agriculture by using RGB cameras, multispectral imaging, LiDAR systems, thermal sensors, and other advanced technologies to enable precision tasks such as targeted fertilizer and pesticide applications, as shown in Figure 4.
3.1 RGB and high-resolution imaging
RGB cameras (visible light: RGB as shown in Figure 3) are high-resolution imaging tools widely used in agricultural UAVs for field mapping and crop monitoring. Operating within the visible light spectrum, these cameras provide detailed visual data on crop conditions, growth trends, and land utilization [1]. When paired with additional sensors, such as multispectral or thermal cameras, RGB cameras enhance the depth and accuracy of collected data, enabling a more comprehensive analysis of agricultural environments [5], as shown in Figure 4(a). The advantages of RGB cameras are versatility and support for a wide range of applications, including crop health monitoring, field mapping, and tracking temporal changes in vegetation [25]. Their high-resolution imagery can identify key issues such as pest infestations, nutrient deficiencies, and signs of water stress [12]. Cost-effectiveness is another significant advantage, as RGB cameras are more affordable than specialized imaging sensors, making them accessible to farmers with varying budgets. Limitations: Despite their utility, RGB cameras have constraints, particularly in the range of spectral data they can capture. For analyses requiring more detailed spectral information, such as detecting subtle plant stress or specific nutrient imbalances, multispectral or hyperspectral sensors are necessary [26], as shown in Figure 4(e). Applications in Agriculture: The integration of RGB cameras in Ag-UAVs has revolutionized farming practices. They are instrumental in various tasks, including crop monitoring, precision agriculture, soil and field mapping, irrigation management, weed detection, yield forecasting, and post-harvest evaluation [13]. These tools provide farmers with actionable insights, enhancing efficiency and productivity across the agricultural cycle [27].
3.2 Multispectral cameras
Applications in Ag-UAVs of multispectral cameras: Multispectral cameras support a wide range of agricultural applications, including crop monitoring, precision farming, and irrigation management [1]. They also aid in land use classification, disease detection, and yield prediction by leveraging VIs like NDVI and advanced tools such as machine learning algorithms [28]. By combining multiple indices, farmers can gain a more comprehensive understanding of vegetation health and variability [19], as shown in Figure 4(f). It is an effective indicator of chlorophyll content and overall crop health during these critical phases. Benefits and Challenges: While multispectral cameras provide non-destructive, highly sensitive monitoring capabilities, challenges such as high initial costs, complex data requiring specialized expertise, and sensitivity to weather conditions persist [5]. However, the long-term benefits, including enhanced productivity, better resource management, and operational cost savings, make these cameras a worthwhile investment for improving agricultural efficiency, as shown in Figure 4.
A transformative tool in Ag-UAVs: Multispectral cameras integrated into agricultural UAVs have become indispensable in modern farming. These cameras operate across specific wavelengths in the electromagnetic spectrum, typically between 400 and 1000 nm, encompassing visible light (RGB) and NIR bands [11], as shown in Figure 3. Their high-resolution imaging capabilities allow for the precise detection of crop health, moisture levels, and nutrient deficiencies, as shown in Figure 4(d). To ensure data accuracy, processes such as atmospheric correction, geometric correction, and radiometric calibration are applied during data analysis.
3.3 Thermal cameras in Ag-UAVs applications
Thermal cameras, equipped with infrared sensors, are invaluable in Ag-UAVs applications. These cameras detect infrared radiation emitted by objects, enabling non-contact temperature measurements within the 800–1400 nm wavelength range coverage as shown in Figure 5(a). This capability supports critical tasks such as assessing plant health and optimizing irrigation by identifying subtle temperature variations. Thermal imaging has transformed agricultural practices, enabling precision monitoring and resource optimization while supporting sustainable farming practices [29]. By integrating these cameras into Ag-UAVs, farmers gain access to detailed, actionable insights that improve decision-making and productivity [30] in Eq. (2).
Figure 5.
Applications of thermal cameras in innovative solutions of Ag-UAVs for crop monitoring, managing, and optimizing agricultural practices include irrigation management: (a) Thermal cameras equipped with thermal infrared sensors the 800–1400 nm, (b) Crop monitoring, (c) Irrigation management, and (d) Distance: The spatial separation between the thermal camera and the target affects.
Where:
TVDI = the Temperature-Vegetation Dryness Index. LST = Land surface temperature (LTS) at a given pixel (Thermal cameras equipped with thermal infrared sensors the 800–1400 nm) as shown in Figure 5(c). LSTmin = Minimum LST for a given NDVI value (wet edge). LSTmax = Maximum LST for a given NDVI value (dry edge).
Key Steps:
Plot the LST vs. NDVI for the study area.
Identify the wet edge (low LST) and dry edge (high LST) by fitting linear relationships to the lower and upper boundaries of the scatterplot: wet edge:
LSTmin (NDVI) =awet NDVI +bwet, and dry edge:LSTmin (NDVI) =awet NDVI +bwet. Substitute these linear equations into the TVDI Eq. to calculate it for each pixel [31]. A simplified version can be expressed as in Eq. (3):
Where:
This method allows for the computation, which serves as a spatial measure for assessing drought intensity and soil moisture levels. The linear coefficients such as (
Key elements involved in this process include:
By leveraging these parameters, TVDI provides a comprehensive framework for identifying variations in soil moisture and drought conditions across landscapes. This tool supports precision agriculture by guiding irrigation strategies and assessing environmental stress on crops as shown in Figure 5.
3.3.1 Key measurements and parameters
Key measurements and parameters of thermal imaging relies on various parameters for accurate assessments as shown in Figure 5(a).
Distance: The spatial separation between the thermal camera and the target affects radiation intensity. Accurate readings are achieved when the camera operates within its calibration distance, defined during manufacturing. Significant deviations from this range can lead to measurement inaccuracies, as shown in Figure 5(c).
Relative humidity (RH): Reflecting environmental moisture content, RH impacts the accuracy of temperature readings. While a default of 70% is typical, adjustments can range from 20–100%, as shown in Figure 5(a).
Emissivity: This measures a surface’s efficiency in emitting thermal radiation. Materials like plants and soil have specific emissivity values, which must be properly configured to avoid errors. Surface conditions, such as corrosion, can alter emissivity, necessitating calibration as shown in Figure 5(a).
Reflected temperature: This accounts for energy reflected by nearby objects. If no extreme temperature sources are nearby, the reflected temperature should align with the ambient environment as shown in Figure 5(d).
Ambient temperature: Representing the air temperature between the camera and the target, this parameter is adjusted based on environmental conditions. Advanced systems incorporate sensors to automatically detect and set this value as shown in Figure 5(d).
Thermal cameras can operate across a wide ambient temperature range, from −40–80°C (−40°F to 176°F), as shown in Figure 5(d).
Applications of the Temperature-Vegetation Dryness Index (TVDI) in agriculture as in Eqs. (3) and (4).
Irrigation management: Thermal imaging helps monitor crop thermal signatures, allowing farmers to optimize water usage and ensure efficient irrigation. It can also estimate soil moisture levels, improving irrigation schedules and crop yield outcomes [30] as shown in Figure 5(c).
Plant health monitoring: By identifying temperature variations that indicate stress, thermal cameras enable early detection of issues like pest infestations or nutrient deficiencies [32] as shown in Figure 5(d).
Drought assessment: TVDI is a drought indicator that correlates land surface temperature (LST) with vegetation health. Calculated using LST and NDVI, TVDI evaluates soil moisture status and drought severity. Higher values indicate severe drought, while lower values suggest milder conditions [31], as in Eqs. (3) and (4).
3.3.2 LiDAR systems
LiDAR (Light Detection and Ranging) is a remote sensing technology that uses pulsed laser beams to measure distances to various surfaces on Earth. In agricultural UAV applications, LiDAR is widely utilized for precise mapping of terrain, crop monitoring, and assessing biomass to model the functioning of a LiDAR system mounted on Ag-UAVs [23]. The key of considerations include both LiDAR and photogrammetric principles. Several critical parameters affect the effectiveness of LiDAR data collection: Transmitted Power (
Target reflectivity (
Distance of LiDAR to target (
Where:
LiDAR technology works by emitting laser pulses toward a target and measuring the time it takes for the reflected pulses to return to the sensor, allowing for precise distance measurements. Time-of-flight (TOF) LiDAR operates similarly to radar, but it uses light pulses instead of microwaves [33]. A TOF LiDAR system includes a laser transmitter that sends out rapid light pulses, a photoreceiver circuit that detects and times the pulses, and optics that focus the reflected light onto the receiver. The round-trip time (τ) between the emission and reflection of the light pulse is used to calculate the target distance (R) by accounting for the speed of light in a vacuum (c) and the refractive index of the optical path (n) in Eq. (5).
Where:
The swath width of a LiDAR system is determined by factors such as the scan angle of the instrument and the altitude of the aircraft. When adjusting for boresight angles, it is crucial to utilize georeferenced points. To estimate the boresight angles, an optimization model is used, which incorporates the georeferencing process in relation to swath width, considering the scan angle of the instrument and the flying height of the UAV [25]. This model allows for the accurate calculation of the swath width based on these parameters. For each LiDAR return, georeferencing can be performed according to a specified equation that integrates these factors to ensure precision in the measurements [34] in Table 2 as follows in Eq. (6):
| Index | Sensor | Eq. | Ref. |
|---|---|---|---|
| the reflectance of the target feature | LiDAR/Radar/RGB Imagery | [14] | |
| Offset target | LiDAR/Radar | [34] | |
| Automatic identification and mapping of /model performance assessment | Multispectral /Hyperspectral camera /RGB imagery /LiDAR/ Radar | [25] | |
| [25] | |||
| [25] | |||
| [25] | |||
| [25] | |||
| Simple ratio between the size of the pattern in the real world and the image is used to convert the image’s horizontal position error to the world frame | Multispectral/Hyperspectral Camera/RGB Imagery/LiDAR/Radar | WorldPositionxy(m) = WorldPositionZ(m) = | [35] |
| The distance a single photon has traveled to and from an object is calculated | |||
| The distance a single photon has traveled to and from an object | LiDAR/Radar | d = c t/2, | [33] |
| Phase shift measurement (PMS) | LiDAR/Radar | d = cΔθ/2πf | [33] |
Table 2.
Key equations governing sensors of lidar and radar provide to determine the effective monitoring range in plant data by measuring variations in light travel time and reflection in Ag-UAVs.
Where:
SL = Swath width as a function of instrument scan angle and Ag-UAVs flying height shown in Figure 6. FOV Field of view. AGL = Above Ground Level of LiDAR scanner FOV (m).
Figure 6.
The imaging equation aids in estimating parameters of swath width as a function of instrument scan angle and Ag-UAVs flying height in LiDAR system in Ag-UAVs.
The point density of the scan is the following in Eq. (7):
Where:
Point Density = Point density of the scan.
LiDAR technology provides high-precision data by measuring variations in light travel time and reflection, allowing for the creation of detailed three-dimensional maps. This level of accuracy is especially valuable in agriculture, where spatial data is crucial for decision-making. In agricultural UAV applications, LiDAR plays a vital role in surveying and mapping, helping farmers assess terrain and crop conditions more effectively [23]. By capturing precise spatial information, it supports the analysis of land features, water distribution, and plant health, ultimately optimizing resource management and improving productivity in agricultural practices as shown in Figure 6.
3.4 Radar technology
Synthetic Aperture Radar (SAR) technology is critical for accurate height measurement and agricultural monitoring when integrated into Ag-UAVs [36]. SAR uses the UAV’s movement to simulate a larger antenna, producing high-resolution imagery of the ground and effectively measuring surface heights [36]. Different frequency bands such as L-band, C-band, and X-band are utilized, with the L-band being particularly useful in agriculture due to its superior ability to penetrate plant canopies. For precise data analysis, SAR data undergoes various processing techniques like signal filtering, noise reduction, and interferometric processing, which convert radar signals into accurate height measurements. Combining radar data with optical and multispectral sensor outputs enhances the overall accuracy, offering a more complete view of the agricultural landscape. In terms of data alignment [33], it is important to adjust coordinate systems to ensure consistency across measurements. The UAV’s coordinate system is used as the reference, with necessary rotations applied to the radar and Inertial Measurement Unit (IMU) data to achieve synchronization [8]. The radar outputs include critical metrics like the Radar Cross Section (RCS), which indicates the strength of reflection from an object, and range rate, representing the velocity of an object relative to the radar sensor [33]. This rich data set, which also includes range, azimuth, and elevation, contributes to the comprehensive monitoring and analysis of agricultural fields as shown in Figure 6 as follows in Eqs. (8)–(10).
Where:
The following terms relate to the measurements and orientations used in UAV flight dynamics:
These parameters are essential for accurate positioning and navigation of Ag-UAVs in various applications. A bumper system in Ag-UAVs typically uses proximity sensors to detect nearby obstacles or the ground in Table 2. These systems often incorporate infrared (IR) sensors for measuring distances, providing a means to prevent collisions and ensure safe flight operations. The detection distance of such systems can be modeled using an equation similar to radar-based measurements, accounting for factors such as sensor calibration and environmental conditions as shown in Figure 7. The specific distance measurement can be calculated using the following in Eq. (11).
Figure 7.
The coordinate system of the UAV is designated as the target reference system. Both the Inertial Measurement Unit (IMU) and radar are adjusted accordingly to align with this system. (a) illustrates the radar sensor’s field of view and the orientation axes of both the radar and the IMU on the Ag-UAV (
Where:
By adjusting the system to accurately measure this time delay, the bumper system can effectively monitor its proximity to obstacles, ensuring safety during Ag-UAVs operations.
4. Components and optimization in recent advances, new perspectives in technology of Ag-UAVs
Ag-UAVs are made up of several essential components that optimize their performance for precision farming. The airframe, often made of lightweight yet durable materials, forms the structural backbone of the UAV, ensuring strength while maintaining aerodynamics for efficient flight [8]. The propulsion system, consisting of motors and propellers, is crucial for providing the necessary lift and maneuverability, directly affecting both flight duration and operational capabilities [13]. The flight control system, which includes various sensors, gyroscopes, and accelerometers, is responsible for stabilizing the UAV during flight. Additionally, GPS technology is typically integrated into the system to provide precise positioning, ensuring accurate navigation during agricultural operations. These systems work together to enable Ag-UAVs to perform a wide range of tasks, from monitoring crop health to mapping fields efficiently [37], as shown in Figure 8.
Figure 8.
Main Components of Ag-UAVs: (a) Airframe for autonomously spraying fertilizers and pesticides, (b) FCS and autonomous operating systems, (c) Ground Control Stations (GCS), and (d) Real-time operations.
4.1 GPS module technology in agricultural UAVs
The GPS module in agricultural UAVs integrates key components such as satellite systems, ground control stations, receivers, software, and mapping tools. Satellites transmit signals that enable the receiver to calculate precise locations by analyzing the signal travel time. GCS ensures satellite functionality and maintains accurate orbital paths [32]. UAV-installed GPS receivers process data from multiple satellites, often supported by Geographic Information Systems (GIS), which create detailed, actionable maps. This technology is highly valued for its precision, ability to cover vast areas efficiently, and real-time data access. However, challenges like signal interference, high costs, and complex data management can hinder widespread use. Despite these limitations, the long-term benefits, including enhanced productivity and cost savings, often outweigh initial investment challenges [38]. GPS modules in UAVs rely on microcontrollers or processors to interpret signals and integrate them with onboard systems like navigation and flight controls. Integration with Inertial Measurement Units (IMUs) improves accuracy by providing data on orientation, speed, and acceleration. Advanced algorithms and sensor fusion techniques enhance reliability, while robust communication protocols ensure seamless operation. A stable power source, typically from the UAV’s primary battery, is essential for consistent GPS functionality [8], as shown in Figure 8(b).
4.2 Flight control systems (FCS)
Flight Control Systems (FCS) and Autonomous Features in Agricultural UAVs: Flight control systems are fundamental for maintaining stability, precise navigation, and efficient operation of agricultural UAVs. These systems utilize a microcontroller to process sensor data and execute control algorithms. By integrating inputs from GPS and IMU sensors, they accurately determine the UAV’s position and orientation, ensuring smooth flight. The IMU, comprising accelerometers and gyroscopes, provides real-time feedback on movement, aiding in stability during flight [8], as shown in Figure 8(b). Key features of FCS include stabilization, autonomous navigation, and real-time sensor data processing. User-friendly interfaces make these systems accessible to operators with varying technical expertise, encouraging broader adoption. However, challenges persist, such as the high cost of advanced flight controllers, the need for technical training, and compliance with aviation regulations across regions. Addressing these concerns is crucial for maximizing UAV efficiency and unlocking their full potential in agriculture.
4.3 Autonomous systems
Autonomous systems within the flight control units (FCUs) of commercial agricultural UAVs are essential for efficient flight management, stability, and task execution. These systems play a key role in precision farming by facilitating tasks such as crop mapping and monitoring and optimizing inputs like water, fertilizers, and pesticides [39, 40]. The integration of autonomous flight control allows UAVs to cover large agricultural areas without the need for constant human oversight, making them ideal for scalable operations. Advanced flight controllers process data from various sensors in real time, enabling quick decision-making and providing farmers with timely insights on crop conditions. Additionally, modern controllers integrate seamlessly with technologies like GPS, LiDAR, and multispectral cameras, which enhance capabilities in crop health assessment and yield prediction [23]. User-friendly interfaces make these sophisticated systems accessible even to those with limited technical knowledge. Despite the benefits, the high cost of quality flight controllers may be a barrier for smaller-scale operations, and the complexity of the technology often requires training for proper usage as shown in Figure 8(c).
4.4 Operating systems
Operating systems play a vital role in enhancing the precision and efficiency of agricultural UAVs [39]. These systems are powered by applications designed for flight and mission planning, allowing operators to plan and optimize UAV routes based on specific agricultural needs. These tools ensure that key tasks, such as crop monitoring, fertilization, and pesticide spraying, are carried out effectively [41]. By automating flight paths, these systems ensure optimal UAV performance in various agricultural environments, making them integral to precision farming practices as shown in Figure 8(c).
4.5 Ground control stations (GCS)
GCS are crucial in managing UAV operations, providing a centralized platform for real-time flight monitoring and control [6]. The GCS enables operators to oversee UAV movements, monitor flight status, and maintain communication links with the UAVs during operations. Specialized software within the GCS also supports tasks like automated spraying and sowing, leveraging sensor data and algorithms to ensure precise application of resources [10]. This integration of technologies ensures that Ag-UAVs are used to their full potential, improving crop health and boosting yields while promoting sustainable farming practices as shown in Figure 8(c).
4.6 Flight planning and mission tools
Flight planning applications and mission scheduling tools are critical for optimizing UAV operations in agricultural settings. These tools automatically generate flight paths based on mission objectives and terrain, allowing UAVs to efficiently cover large areas [38]. Real-time monitoring capabilities provide constant updates on flight status, helping operators make quick adjustments if needed. Additionally, mission planning tools help coordinate UAV operations to align with the needs of crops and environmental conditions, ensuring that agricultural tasks are completed on time and efficiently, as shown in Figure 8(c). Data analysis tools, such as those processing NDVI for crop health assessments, offer valuable insights that enhance farm management decisions.
4.7 Real-time operations
Real-time operations are at the core of enhancing Ag-UAV efficiency and precision in farming practices. These operations utilize flight planning applications, ground control stations, data links, and specialized software for dynamic agricultural tasks, such as crop surveillance, spraying, and sowing [6]. By incorporating real-time data, including weather, field conditions, and crop health metrics, flight paths are optimized to maximize coverage and reduce flight time. The GCS serves as the command center, allowing operators to monitor flight status and manage UAV operations [42]. Data links ensure continuous communication between the UAVs and the GCS, enabling real-time adjustments based on telemetry data and enhancing the overall operational effectiveness.
4.8 Spraying system
Agricultural UAVs have revolutionized crop management, particularly in the application of fertilizers and pesticides, by integrating advanced spraying systems for precision agriculture [43]. These systems enable targeted delivery, reducing waste and enhancing efficiency. Essential components include specialized nozzles like centrifugal and electrostatic types. Centrifugal nozzles produce fine droplets for uniform coverage, while electrostatic nozzles improve adhesion to plant surfaces, reducing chemical drift [44] as shown in Figure 8(d). For the application of UAVs in plant protection field, obtaining the distribution law of the unique downwash air flow is the key step to control and improve spraying quality [45] and other integral parts of the spraying system include:
Pump System: Ensures consistent fluid flow during operation.
Liquid Tank: Designed for easy refilling and maintenance.
Control Mechanisms: Employ electronics and software to regulate spray patterns and rates.
Sensors: Monitor environmental factors, such as wind speed and temperature, to optimize spraying conditions [46].
Flight Control Integration: Maintains UAV stability and precise navigation during applications.
The advantages of UAV spraying systems are notable, including precision application, reduced environmental impact, and the ability to cover extensive areas quickly, as shown in Table 3. However, barriers such as high setup costs, regulatory hurdles, and the need for skilled operation can affect widespread adoption [7]. Despite these challenges, the long-term benefits, such as reduced chemical usage, improved crop health, and labor efficiency, make these systems economically viable [42]. The effectiveness of spraying operations is influenced by factors like droplet dynamics, spray uniformity, nozzle design, flight altitude, and environmental conditions [44]. For example, the evaporation rate of sprayed liquids depends on temperature and relative humidity. An equation modeling chemical deposition on crop surfaces typically incorporates these variables to ensure optimal coverage and adherence. By combining precision technology and efficient design, UAV spraying systems contribute to sustainable and productive agricultural practices as follows in Eqs. (12) and (13).
| Index | Factors | Eq. | Ref. |
|---|---|---|---|
| Operation parameters and spraying liquid configuration Coefficient of variation | spraying operations | [44] | |
| Deposition level | Uniformity/ Nozzle design | [44] | |
| Drift rate and percentage | Uniformity/ Nozzle design | [44] | |
| the reflectance of the target feature | flight altitude, and environmental condition | [14] |
Table 3.
The effectiveness of spraying operations is influenced by factors like droplet dynamics, spray uniformity, nozzle design, flight altitude, and environmental conditions.
A simplified version can be expressed as follows in Eq. (13):
Where:
The distribution of chemicals from agricultural UAVs depends on various factors:
4.9 Sowing systems
Sowing systems integrated into Ag-UAVs are designed to automate the seed planting process, delivering enhanced efficiency and precision in modern farming [47]. These systems combine advanced technology and engineering to optimize seeding operations across diverse terrains and crop requirements [10]. These systems bring significant advantages, including reduced labor costs, faster sowing times, and the ability to work in challenging terrains where traditional methods may be less effective [42]. However, factors such as initial investment, maintenance requirements, and the need for technical expertise should be carefully evaluated to ensure long-term viability. By leveraging advanced navigation, data integration, and adaptive controls, UAV sowing systems are paving the way for more sustainable and precise agricultural practices in Table 4.
| Key components | Details |
|---|---|
| Seed dispensers | Critical for the controlled distribution of seeds, these are available in pneumatic, mechanical, or gravity-fed configurations. Each type is suited for different seed sizes and planting environments, ensuring flexibility in agricultural operations. |
| GPS navigation system | High-precision navigation, often supported by RTK (Real-Time Kinematic) technology, enables accurate seed placement, minimizing wastage and ensuring uniformity in sowing patterns. |
| Control systems | These systems integrate flight management software with real-time sensors, allowing adjustments to flight paths and seeding parameters based on field conditions, maximizing operational effectiveness. |
| Data analytics tools | Tools such as soil moisture sensors and remote sensing technologies provide critical insights into soil conditions, weather patterns, and field topography [48]. This data supports informed decision-making and enhances the overall planting strategy. |
| Payload optimization | The UAV’s payload capacity is a key factor, determining the volume of seeds that can be carried and distributed in a single flight, which directly impacts efficiency and coverage. |
Table 4.
Key components are designed to automate the seed planting process, delivering enhanced efficiency in Ag-UAVs.
5. Applications and innovative solutions of Ag-UAVs for crop monitoring, managing, and optimizing agricultural practices
5.1 Crop monitoring and crop health assessment
The adoption of Ag-UAVs for crop monitoring has revolutionized the way farmers assess crop health [3]. These UAVs, equipped with advanced imaging systems like multispectral and hyperspectral cameras, enable precise analysis of agricultural fields over large areas. High-resolution aerial imagery captured by these drones facilitates the calculation of vegetation indices, such as the NDVI [17]. This index is instrumental in detecting crop stress, nutrient imbalances, and water deficiencies, allowing for timely adjustments to farming practices in Table 5. These models help optimize UAV utilization, ensuring maximum impact on crop management as follows in Eqs. (14) and (15).
| Key components | Details |
|---|---|
| Enhanced decision-making | Real-time data collection supports precise actions for irrigation, fertilization, and pest management, optimizing resource use and boosting yields [6]. |
| Targeted crop management | Frequent surveys provide detailed insights into crop health variability across fields, enabling specific interventions that minimize waste and environmental impact [36]. |
| Applications of VIs: | Indices like NDVI empower farmers to monitor plant health effectively and respond promptly to emerging issues. This capability not only improves productivity but also promotes long-term agricultural sustainability [16]. |
| Representation of Ag-UAVs efficiency | The operational effectiveness of UAVs in agriculture can be quantified using mathematical models that integrate factors such as imaging resolution, flight coverage, and the frequency of data acquisition [39]. |
| Sustainability | By reducing unnecessary inputs and focusing resources where they are most needed, UAVs contribute to more sustainable farming practices [1]. |
Table 5.
Benefits of based monitoring in applications and innovative solutions of Ag-UAVs.
Where:
α1,α2,…,α7α1,α2,…,α7 are weighting factors that reflect the importance of each parameter in a specific agricultural setting.
VIs = effective vegetation monitoring is vital for understanding plant health and growth patterns. Indices such as NDVI, SAVI, EVI, NDRE, OSAVI, and TVDI in Table 1.
Looking ahead, future trends suggest a greater integration of artificial intelligence (AI) for predictive analytics, allowing farmers to anticipate and address potential issues like disease outbreaks or yield deficits [52]. The integration of advanced imaging technologies, such as hyperspectral sensors, into Ag-UAVs provides a practical and accessible tool for users, facilitating high-resolution data acquisition and comprehensive of agricultural crop analysis [53, 54]. Additionally, the Internet of Things (IoT) is emerging as a transformative force, connecting devices like sensors and drones for real-time monitoring and decision-making [52]. This interconnected approach supports precision agriculture by enabling continuous data flow and responsive farming practices, ultimately driving sustainability and productivity.
5.2 Field crop monitoring precision and yield prediction
The adoption of Ag-UAVs in field crop monitoring precision and yield prediction has revolutionized how data is collected and analyzed, enabling farmers to optimize their practices with unprecedented accuracy [5]. Equipped with cutting-edge imaging tools like multispectral and thermal cameras, UAVs capture detailed aerial data about fields. This data allows for in-depth analysis of crop health, soil quality, and environmental factors, aiding in smarter decision-making [55]. Ag-UAVs empower farmers to take a targeted approach to resource application. For instance, VIs like NDVI in Table 1 help pinpoint areas needing specific inputs such as water or fertilizers [56]. This precise intervention minimizes waste, optimizes resource use, and reduces environmental impact while enhancing crop yields [21] as shown in Figure 9(a). Regular UAV surveys throughout the growing season further support dynamic adjustments in management practices, promoting overall efficiency and sustainability. Developing a model to assess agricultural productivity using Ag-UAVs would involve variables that address crop health, field conditions, and yield metrics [40]. Such a framework could serve as a robust tool for optimizing agricultural outcomes while promoting eco-friendly practices, as follows in Eq. (16).
Figure 9.
Future and Trends of Ag-UAVs: (a) Crop monitoring and crop health assessment and (b) Crop management.
Where:
The key factors that contribute to agricultural productivity can be expressed as follows:
5.3 Assessing agricultural productivity
Agricultural productivity can be effectively evaluated by employing models that incorporate key indicators such as NDVI, crop height in Table 2, and soil moisture levels in Eq. (4). A weighted approach allows for the assessment of each factor’s contribution to overall productivity, enabling a more nuanced understanding of crop performance and resource needs in Eq. (17).
Where:
The key factors that contribute to assessing agricultural productivity can be expressed as follows:
5.4 Precision and assessing productivity
Precision agriculture is significantly enhanced by the utilization of Ag-UAVs. Equipped with advanced imaging technologies, such as multispectral and thermal cameras, UAVs enable farmers to collect high-resolution aerial data regarding their fields. This data facilitates a comprehensive analysis of crop health, soil conditions, and environmental factors, thereby supporting more informed decision-making processes [40]. In the context of precision agriculture, Ag-UAVs empower farmers to implement targeted interventions based on real-time data. By employing indices such as the NDVI, farmers can identify specific areas that require tailored inputs, such as fertilizers or irrigation, optimizing resource utilization and minimizing waste [15]. This targeted approach not only enhances crop yields but also reduces environmental impact by ensuring that inputs are applied only where needed. Additionally, Ag-UAVs play a crucial role in monitoring crop growth throughout the growing season, allowing farmers to dynamically adjust their management practices, which ultimately improves overall farm efficiency and sustainability [40].
Tools of precision in Ag-UAVs such as multispectral and hyperspectral imaging facilitate early detection of plant stress and disease Ag-UAVs have emerged as essential components of precision agriculture, offering high-resolution spatial data and the ability to cover extensive areas efficiently. Equipped with various sensors, UAVs capture images across different spectral bands, enabling comprehensive assessments of plant health and environmental conditions [32]. Additionally, ground-based sensors measure critical parameters such as soil properties and weather conditions, delivering real-time data that can be integrated with remote sensing information to enhance decision-making processes [15]. The integration of advanced data analytics and machine learning algorithms is crucial for interpreting the large datasets generated by UAVs and sensors. These technologies support the prediction of crop yields, identification of potential issues, and optimization of resource allocation.
6. Future and trends of Ag-UAVs
6.1 AI integration in Ag-UAVs
The integration of AI in Ag-UAVs is poised to revolutionize farming by enhancing operational efficiency and productivity. AI-driven advancements are shaping tools like flight and mission planning applications, enabling the automation of complex tasks and improving the accuracy of decision-making processes. These innovations empower farmers to optimize workflows and adapt to real-time field conditions [34] as shown in Figure 9(a). AI enhances UAV capabilities in multiple applications. Equipped with sensors such as multispectral and hyperspectral cameras, UAVs collect detailed imagery and data that AI algorithms analyze to assess crop health, detect pest activity, and monitor growth stages. Machine learning models process this data to generate actionable insights, supporting farmers in tailoring their interventions to specific crop needs [59] as shown in Figure 9.
Precision operations powered by AI: AI-equipped UAVs play a pivotal role in precision agriculture. They can assess soil health by mapping properties and detecting nutrient deficiencies, providing critical information for determining fertilizer and irrigation needs. This targeted approach minimizes resource wastage while boosting yield potential [37]. Furthermore, precision spraying systems integrated with AI allow UAVs to identify and treat specific areas based on real-time conditions, reducing chemical use and mitigating environmental impacts as shown in Figure 9(b).
Yield predictions and decision support: AI enhances yield prediction by analyzing historical data and current crop metrics, offering valuable insights for harvest planning and market strategies [15]. The ability to integrate UAV-collected data with external information, such as weather forecasts and market trends, enables comprehensive decision support systems [56]. These systems not only improve productivity but also promote sustainable agricultural practices by optimizing resource use and reducing environmental footprints.
Tools and advancements in precision agriculture: Ag-UAVs are pivotal in precision farming, leveraging advanced imaging technologies like multispectral and hyperspectral cameras to detect early signs of plant stress or disease [12] as shown in Figure 9(a). These UAVs efficiently collect high-resolution spatial data, covering extensive areas and offering detailed insights into plant and environmental conditions. The data, combined with ground-based sensors that measure soil and weather parameters, creates a comprehensive framework for informed decision-making [16].
Integration of advanced technologies: the application of advanced analytics and machine learning enhances the value of the data gathered by UAVs and sensors [54]. These technologies process large datasets to predict crop yields, identify potential issues, and optimize input distribution, ultimately improving productivity and sustainability [39]. By integrating remote sensing with ground-based observations, farmers gain a holistic view of their fields, supporting proactive management strategies [1].
The future of Ag- UAVs lies in leveraging AI to foster smarter, data-driven farming, ultimately transforming traditional methods into sustainable and efficient agricultural ecosystems as shown in Figure 9.
6.2 Utilization of agricultural UAVs
The application of Agricultural UAVs (Ag-UAVs) is growing rapidly across various farming practices, including fertilizer application, monitoring vegetation growth, and assessing crop yields [17]. This expansion is driven by advances in technology, a focus on increasing agricultural efficiency, and global efforts to meet sustainability goals. Emerging trends suggest a shift toward automation and the integration of AI to optimize UAV operations. AI-driven systems enhance flight path planning and enable real-time analytics, improving adaptive spraying mechanisms that minimize chemical waste and environmental impact [7]. Ag-UAVs are becoming a cornerstone of precision agriculture, particularly with the use of hyperspectral and multispectral imaging. These technologies facilitate the early detection of pests and diseases, allowing for prompt interventions to safeguard crop health [51]. The large datasets generated by UAVs on crop conditions and field variability are processed using advanced analytical platforms, offering actionable insights to improve farm productivity and sustainability. Sustainability remains a key focus, with Ag-UAVs enabling targeted application techniques that reduce chemical usage. This includes using bio-compatible fertilizers and environmentally friendly crop protection measures [60]. Real-time pest detection, aided by AI and thermal imaging, allows for dynamic responses, such as applying treatment exclusively to affected areas, thereby reducing costs and improving crop outcomes [6]. Moreover, regulatory frameworks around the globe are adapting to better accommodate the integration of UAVs in agriculture. These frameworks address issues of safety, operational guidelines, and data privacy, creating a conducive environment for the widespread adoption of Ag-UAVs in modern farming practices.
7. Conclusion
In summary, the integration of UAVs into modern agricultural systems marks a pivotal shift toward more efficient and sustainable farming practices. With the use of various sensors, such as RGB, multispectral, thermal cameras, LiDAR, and radar technology, Ag-UAVs provide precise monitoring of crop health and optimize resource management. Advanced flight control systems and GPS enable accurate navigation, allowing for data-driven decision-making that improves efficiency while minimizing environmental impact. Ag-UAVs will play an increasingly vital role in boosting productivity and promoting sustainable food production. The integration of advanced technologies such as AI, multispectral imaging, and LiDAR into Ag-UAVs is driving a transformation in agriculture. These tools offer significant benefits, including improved productivity, enhanced resource management, and reduced environmental impact. Future advancements are expected to further optimize agricultural operations, paving the way for sustainable and efficient farming practices.
Acknowledgments
This research project has been funded by Mahidol University (Fundamental Fund: fiscal year 2021 by National Science Research and Innovation Fund (NSRF).
References
- 1.
Ahmed S, Basu N, Nicholson CE, Rutter SR, Marshall JR, Perry JJ, et al. Use of machine learning for monitoring the growth stages of an agricultural crop†. Sustainable Food Technology. 2024; 2 :104-125. DOI: 10.1039/d3fb00101f - 2.
Feng T, Lei J, Zeng Y, Qin X, Wang Y, Wang D, et al. Three-dimensional path-following control method for flying–walking power line inspection robot based on improved line of sight. Aerospace. 2023; 10 (945):1-21. DOI: 10.3390/aerospace10110945 - 3.
Kazemi F, Parmehr GE. Evaluation of RGB vegetation indices derived from uav images for rice crop growth monitoring. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; 19–22 February 2023, Tehran, Iran (Virtual). GeoSpatial Conference 2022 (X-4/W1–2022). Tehran, Iran (virtual): ISPRS Journal Ph & RS; 2022. pp. 385-390. DOI: 10.5194/isprs-annals-X-4-W1-2022-385-2023 - 4.
Gallo I, Rehman AU, Dehkord RH, Landro N, La Grassa R, Boschetti M, et al. Deep object detection of CropWeeds: Performance of YOLOv7 on a real case dataset from UAV images. Remote Sensing. 2023; 15 (539):1-13. DOI: 10.3390/rs15020539 - 5.
Mukiibi A, Machakaire ATB, Franke AC, Steyn JM. A systematic review of vegetation indices for potato growth monitoring and tuber yield prediction from remote sensing. Potato Research. 2004; 133 :1-40. DOI: 10.1007/s11540-024-09748-7 - 6.
Alexandris S, Psomiadis E, Proutsos N, Philippopoulos P, Charalampopoulos I, Kakaletris G, et al. Integrating drone technology into an innovative agrometeorological methodology for the precise and real-time estimation of crop water requirements. Hydrology. 2021; 8 :131. DOI: 10.3390/hydrology8030131 - 7.
Chen P, Douzals JP, Lan Y, Cotteux E, Delpuech X, Pouxviel G, et al. Characteristics of unmanned aerial spraying systems and related spray drift: A review. Frontiers in Plant Science. 2022; 13 :870956. DOI: 10.3389/fpls.2022.870956 - 8.
Anderson K, Gaston KJ. Lightweight unmanned aerial vehicles will revolutionize spatial ecology. Frontiers in Ecology and the Environment. 2013; 11 (3):138-146. DOI: 10.1890/120150 - 9.
Daniels L, Eeckhout E, Wieme J, Dejaegher Y, Audenaert K, Maes WH. Identifying the optimal radiometric calibration method for UAV-based multispectral imaging. Remote Sensing. 2023; 15 (2909):1-22. DOI: 10.3390/rs15112909 - 10.
Lysych M, Bukhtoyarov L, Druchinin D. Design and research sowing devices for aerial sowing of Forest seeds with UAVs. Inventions. 2021; 6 :83. DOI: 10.3390/inventions6040083 - 11.
Gitelson A, Merzlyak MN. Signature analysis of leaf reflectance spectra: Algorithm development for remote sensing of chlorophyll. Journal of Plant Physiology. 1996; 148 (s3–4):494-500. DOI: 10.1016/S0176-1617(96)80284-7 - 12.
Bock CH, Nutter Jr. FW. Detection and measurement of plant disease symptoms using visible-wavelength photography and image analysis. Perspectives in Agriculture, Veterinary Science, Nutrition and Natural Resources. 2021; 6 (27):1-15. DOI: 10.1079/PAVSNNR20116027 - 13.
Deng L, Mao Z, Li X, Hu Z, Duan F, Yan Y. UAV-based multispectral remote sensing for precision agriculture: A comparison between different cameras. ISPRS Journal of Photogrammetry and Remote. 2018; 14 :124-136. DOI: 10.1016/j.isprsjprs.2018.09.008 - 14.
Xu S, Xu X, Blacker C, Gaulton R, Zhu Q, Yang M, et al. Estimation of leaf nitrogen Contentin Rice using vegetation indices and feature variable optimization with information fusion of multiple-sensor images from UAV. Remote Sensing. 2023; 15 :854. DOI: 10.3390/rs15030854 - 15.
Guebsi R, Mami S, Chokmani K. Drones in precision agriculture: A comprehensive review of applications, technologies, and challenges. Drones. 2024; 8 (686):1-30. DOI: 10.3390/drones8110686 - 16.
Qi J, Chehbouni A, Huete AR, Kerr YH, Sorooshian S. A modified soil adjusted vegetation index. Remote Sensing of Environment. 1994; 48 :119-126. DOI: 10.1016/0034-4257(94)90134-1 - 17.
Wahab I, Hall O, Jirström M. Remote sensing of yields: Application of UAV imagery-derived NDVI for estimating maize vigor and yields in complex farming Systems in sub-Saharan Africa. Drones. 2018; 2 :28. DOI: 10.3390/drones2030028 - 18.
Zhen Z, Chen S, Yin T, Chavanon E, Lauret N, Guilleux J, et al. Using the negative soil adjustment factor of soil adjusted vegetation index (SAVI) to resist saturation effects and estimate leaf area index (LAI) in dense vegetation areas. Sensors. 2021; 21 (2115):1-14. DOI: 10.3390/s21062115 - 19.
Jianga Z, Huetea AR, Li J, Qi J. Interpretation of the modified soil-adjusted vegetation index isolines in red-NIR reflectance space. Journal of Applied Remote Sensing. 2007; 1 (013503):1-12. DOI: 10.1117/1.2709702 - 20.
Lawrence RL, Ripple WJ. Comparisons among vegetation indices and Bandwise regression in a highly disturbed heterogeneous landscape. Remote Sensing of Environment. 1998; 64 :91-102. DOI: 10.1016/S0034-4257(97)00171-5 - 21.
Steven MD. The sensitivity of the OSAVI vegetation index to observational parameters. Remote Sensing of Environment. 1998; 63 (1):49-60. DOI: 10.1016/S0034-4257(97)00114-4 - 22.
Karmakar P, Teng SW, Murshed M, Pang S. Crop monitoring by multimodal remote sensing: A review. Remote Sensing Applications: Society and Environment. 2024; 33 :101093. DOI: 10.1016/j.rsase.2023.101093 - 23.
Zhao K, García M, Liu S, Guo QC, Gang Zhang X, Zhou Y, et al. Terrestrial lidar remote sensing of forests: Maximum likelihood estimates of canopy profile, leaf area index, and leaf angle distribution. Agricultural and Forest Meteorology. 2015; 209–210 :100-113. DOI: 10.1016/j.agrformet.2015.03.008 - 24.
Huang Y, Ren Z, Li D, Liu X. Phenotypic techniques and applications in fruit trees: A review. Plant Methods. 2020; 16 (107):1-22. DOI: 10.1186/s13007-020-00649-7 - 25.
Beloiu M, Heinzmann L, Rehush N, Gessler A, Griess VC. Individual tree-crown detection and species identification in heterogeneous forests using aerial RGB imagery and deep learning. Remote Sensing. 2023; 15 :1463. DOI: 10.3390/rs15051463 - 26.
Su W, Zhang M, Bian D, Liu Z, Huang J, Wang W, et al. Phenotyping of corn plants using unmanned aerial vehicle (UAV) images. Remote Sensing. 2019; 11 (17):1-19. DOI: 10.3390/rs11172021 - 27.
Freeman PK, Freeland RS. Agricultural UAVs in the U.S.: Potential, policy, and hype. Remote Sensing Applications: Society and Environment. 2015; 2 :35-42. DOI: 10.1016/j.rsase.2015.10.002 - 28.
Impollonia G, Croci M, Ferrarini A, Brook J, Martani E, Blandinières H, et al. UAV remote sensing for high-throughput phenotyping and for yield prediction of Miscanthus by machine learning techniques. Remote Sensing. 2022; 14 (2927):1-24. DOI: 10.3390/rs14122927 - 29.
Bhandari M, Xue Q, Liu S, Stewart BA, Rudd JC, Pokhrel P, et al. Thermal imaging to evaluate wheat genotypes under dryland conditions. Agrosystems, Geosciences & Environment. 2021; 4 :e20152. DOI: 10.1002/agg2.20152 - 30.
Chen A, Jiang J, Luo Y, Zhang G, Hu B, Wan X, et al. Temperature vegetation dryness index (TVDI) for drought monitoring in the Guangdong Province from 2000 to 2019. PeerJ. 2023; 11 (e16337):1-30. DOI: 10.7717/peerj.16337 - 31.
Li H, Li C, Lin Y, Lei Y. Surface temperature correction in TVDI to evaluate soil moisture over a large area. Journal of Food, Agriculture & Environment. 2010; 8 (3&4):1141-1145 - 32.
Awais M, Li W, Hussain S, Cheema MJM, Li W, Song R, et al. Comparative evaluation of land surface temperature images from unmanned aerial vehicle and satellite observation for agricultural areas using In situ data. Agriculture. 2022; 12 :184. DOI: 10.3390/agriculture12020184 - 33.
Farhan SM, Yin J, Chen Z, Memon MS. A comprehensive review of LiDAR applications in crop management for precision agriculture. Sensors. 2024; 24 :5409. DOI: 10.3390/s24165409 - 34.
Almalki FA, Soufiene BO. Modifying Hata-Davidson propagation model for remote sensing in complex environments using a multifactional drone. Sensors. 2022; 22 :1786. DOI: 10.3390/s22051786 - 35.
Moreira M, Azevedo F, Ferreira A, Pedro D, Matos-Carvalho J, Ramos A, et al. Precision landing for low-maintenance remote operations with UAVs. Drones. 2021; 5 (103):1-33. DOI: 10.3390/drones5040103 - 36.
Omia E, Bae H, Park E, Kim MS, Baek I, Kabenge I, et al. Remote sensing in field crop monitoring: A comprehensive review of sensor systems, data analyses and recent advances. Remote Sensing. 2023; 15 :354. DOI: 10.3390/rs15020354 - 37.
FHL F, Heldens WB, Kong Z, Lange ES. Drones: Innovative Technology for use in precision Pest management. Journal of Economic Entomology. 2020; 113 :1-24. DOI: 10.1093/jee/toz268 - 38.
Shamshiri RR, Hameed IA, Balasundram SK, Ahmad D, Weltzien C, Yamin M. In: Luque A, Hegedus S, editors. Books of Agricultural Robots. London, UK: IntechOpen; 2018. pp. 91-114. DOI: 10.5772/intechopen.80936 - 39.
Kim J, Kim S, Ju C, Son H. Unmanned aerial vehicles in agriculture: A review of perspective of platform, control, and applications. IEEE Access. 2019; 7 :105100-105115. DOI: 10.1109/ACCESS.2019.2932119 - 40.
Tsouros DC, Bibi S, Sarigiannidis PG. A review on UAV-based applications for agriculture †. Information. 2019; 10 :349. DOI: 10.3390/info10110349 - 41.
Qi P, Zhang L, Wang Z, Han H, Müller J, Li T, et al. Effect of operational parameters of unmanned aerial vehicle (UAV) on droplet deposition in trellised pear orchard. Drones. 2023; 7 :57. DOI: 10.3390/drones7010057 - 42.
FVAD S. Analysis of preliminary design requirements of a heavy LiftMultirotor drone for agricultural use. Chemical. Engineering Transactions. 2017; 58 :625-630. DOI: 10.3303/CET1758105 - 43.
KRG A. An autonomous UAV for pesticide. Journal of Trend in Scientific Research and Development (IJTSRD). 2019; 3 (3):986-990. DOI: 10.31142/ijtsrd23161 - 44.
Wang J, Ma C, Chen P, Yao W, Yan Y, Zeng T, et al. Evaluation of aerial spraying application of multi-rotor unmanned aerial vehicle for Areca catechu protection. Frontiers in Plant Science. 2023; 14 :1093912. DOI: 10.3389/fpls.2023.1093912 - 45.
Zhang Z, Zhu L. A review on unmanned aerial vehicle remote sensing: Platforms, sensors, data processing methods, and applications. Drones. 2023; 7 (398):1-42. DOI: 10.3390/drones7060398 - 46.
Yang FB, Xue XY, Zhang L, Sun Z. Numerical simulation and experimental verification on downwash air flow of six-rotor agricultural unmanned aerial vehicle in hover. International Journal of Agricultural and Biological Engineering. 2017; 10 (4):41-53. DOI: 10.25165/j.ijabe.20171004.3077 - 47.
Pan Y, Zhu N, Ding L, Li X, Goh H-H, Han C, et al. Identification and counting of sugarcane seedlings in the field using improved faster R-CNN. Remote Sensing. 2022; 14 :5846. DOI: 10.3390/rs14225846 - 48.
Pruthviraj U, Kashyap Y, Baxevanaki E, Kosmopoulos P. Solar photovoltaic hotspot inspection using unmanned aerial vehicle thermal images at a solar field in South India. Remote Sensing. 2023; 15 :1914. DOI: 10.3390/rs15071914 - 49.
Eide A, Koparan C, Zhang Y, Ostlie M, Howatt K, Sun X, et al. UAV-assisted thermal infrared and multispectral imaging of weed canopies for glyphosate resistance detection. Remote Sensing. 2021; 13 (4606):1-18. DOI: 10.3390/rs13224606 - 50.
Kouadio L, El JM, Belabess Z, Laasli SE, Roni MZK, Amine IDI, et al. A review on UAV-based applications for plant disease detection and monitoring. Remote Sensing. 2023; 15 :4273. DOI: 10.3390/rs15174273 - 51.
Neupane K, Baysal-Gurel F. Automatic identification and monitoring of plant diseases using unmanned aerial vehicles: A review. Remote Sensing. 2021; 13 (3841):1-23. DOI: 10.3390/rs13193841 - 52.
Chukwu N, Ogwugwa EC. Applications of artificial intelligence in agriculture: A review. Engineering, technology and applied science. Research. 2019; 9 (4):4377-4383. DOI: 10.48084/etasr.2756 - 53.
Lukas V, Huˇnady I, Kintl A, Mezera J, Hammerschmiedt T, Sobotková J, et al. Using UAV to identify the optimal vegetation index for yield prediction of oil seed rape ( Brassica napus L.) at the flowering stage. Remote Sensing. 2022;14 :4953. DOI: 10.3390/rs14194953 - 54.
Yu J, Wang J, Leblon B. Evaluation of soil properties, topographic metrics plant height and unmanned aerial vehicle multispectral imagery using machine learning methods to estimate canopy nitrogen weight in corn. Remote Sensing. 2021; 13 :3105. DOI: 10.3390/rs13163105 - 55.
Mogili UR, Deepak BBVL. Review on application of drone Systems in Precision Agriculture. Procedia Computer Science. 2018; 133 :502-509. DOI: 10.1016/j.procs.2018.07.063 - 56.
Rejeb A, Abdollahi A, Rejeb K, Treiblmaier H. Drones in agriculture: A review and bibliometric analysis. Computers and Electronics in Agriculture. 2022; 198 :107017. DOI: 10.1016/j.compag.2022.107017 - 57.
Maguire MS, Neale CMU, Woldt WE. Improving: Accuracy of unmanned aerial system thermal infrared remote sensing for use in energy balance models in agriculture applications. Remote Sensing. 2021; 13 (1635):1-17. DOI: 10.3390/rs13091635 - 58.
Yan W, Jiang J, Lanwu H, Zhao W, Nair R, Wang X. Correcting land surface temperature from thermal imager by considering heterogeneous emissivity. International Journal of Applied Earth Observation and Geoinformation. 2024; 129 :103824. DOI: 10.1016/j.jag.2024.103824 - 59.
Ezzy H, Charter M, Bonfante A, Brook A. How the small object detection via machine learning and UAS-based remote-sensing imagery can support the achievement of SDG2: A case study of vole burrows. Remote Sensing. 2021; 13 (3191):1-18. DOI: 10.3390/rs13163191 - 60.
Huu BV, Hieu NQ, Hieu LT. Monitoring growth and predicting crop yield through UAV-mounted spectral camera analysis of the interplay between soil compaction and vegetation index. Emirates Journal of Food and Agriculture. 2024; 36 :1-10. DOI: 10.3897/ejfa.2024.118256