Digital horticulture: An integrated approach of precision agriculture

Introduction

Precision agriculture is a technological farming approach that combines applied technology with controllable temporal and spatial variation principles to enhance crop performance and maintain the natural environment in every aspect of the agricultural industry. (Ahmad et al., 2020) [5] . By precisely determining the necessary amounts of inputs, precision agriculture reduces waste and raises average yields in comparison to conventional farming. The comparatively tiny and dispersed landholdings in India are a significant problem. 58% of India's arable land is owned by a single person and is less than one hectare (Dev and S, 2014) [77] . Seed, soil, water, and agrochemicals (such as fertilizers) interact intricately to form the agricultural production system. Therefore, the long-term functioning of such a complicated system relies on the meticulous monitoring of all inputs. Small fields were common in agriculture before the industrial revolution (Allen and R, 1994) [7] . Without really measuring the variability, farmers used to have a comprehensive picture of their agricultural system. Large-scale, homogenous, mediocre agricultural methods were dominated by mechanization and the drive for more profits (Giller et al., 2021) [48] . The late twentieth and beginning of the twenty-first centuries witnessed innovations in technology that cleared pathways towards the expansion of agriculture. These days, as agricultural profitability declines, producers search for technology that saves expenses without sacrificing output (Jack and K, 2013) [61] . According to Bill No. H.R. 2534 of the US House of Representatives from 1997, in the beginning, precision agriculture has been defined as "an integrated information-and production-based farming system that has the objective at maximizing productivity, profitability, and a long-term location-specific and whole agricultural production efficiency while trimming unwanted effects on wildlife and the environment." Modern methods such as precision farming employ technological advances to reduce hazards and expenses while boosting sustainability, profitability, and performance (Belousova et al., 2019). Management zones provide the use of suitable inputs to optimize management practices, hence enhancing profitability and minimizing environmental effects (Sharma and P, 2007). Precision farming is currently described as "an ecologically sustainable system solution that maximizes product quality and quantity while minimizing expenses, human involvement, and unpredictability caused by unpredictable nature" Precision farming has changed in recent years (Gebbers and Adamchuk, 2010) [47] . Smart agriculture also means a methodology that applies the 4R (right time, right place, right method, and right amount) of agriculture. The technologies like GPS, GIS, Yield Monitoring, Remote Sensing, Variable Rate Technology (VRT), Crop Scouting Devices, Decision Support System (DSS), Farming Management Software, Auto-Steer and Guidance Systems, and Sensor Technologies are the major branches of precision farming (Yadav and Sidana,2023) [156] . The development of sensor technology, which when paired with protocols that connect mapped variables to suitable farming management activities, including growing, sowing, fertilization, herbicide treatment, and harvesting, makes precision agriculture feasible (Monteiro et al., 2021) [88] . Nowadays, artificial intelligence combined with various new developmental technologies like drones, sensors, automated systems, machine learning, and leaf analysis by using graphical interpretation are more feasible towards meeting the global agriculture, food, and production demands.

Rates of Adoption

The adoption rate is substantially greater in developed nations.

According to Leonard (2014), 80% of grain growers in Australia employ automated guiding, while 60% of farmers in the UK use PA in some capacity, mostly GPS steering (Norris, 2015). In developing countries, adoption rates are lower; Brazil reports only 20% adoption overall (Albuquerque, 2017), while in Turkey, only 6% of combines and cotton harvesters are equipped with yield monitors (Keskin et al., 2017) [67] .

Technology Diversity

Developed countries adopt a broader range of technologies, such as variable-rate applications, auto guidance, yield monitoring, and GPS mapping (Schimmelpfennig & Ebel, 2011) [125] . Developing countries primarily rely on basic tools like soil sampling, manual guidance, and navigation aids (Helm, 2005; Akdemir, 2016) [6,57] .

Farmer Usage

In developed nations, large-scale adoption is common across regions andcrops, with 83% of US agricultural input dealers offering GPS guidance systems (Erickson & Widmar, 2015) [15] . Adoption in developing countries is often localized and cropspecific. For example, laser levelling is primarily used in rice farming in India (Mondal and Basu, 2009) [87] .

Economic Barriers

High costs pose minor barriers in developed countries, where farmers generally have access to subsidies and advanced equipment (Schimmelpfennig, 2016) [125] . Developing countries face significant financial challenges, as seen in Russia, where PA adoption remains slow due to high costs (Anonymous, 2013).

Focus Areas

 Developed countries focus on advanced automation, for example, variable-rate fertilizer treatments and sowing (Lowenberg-DeBoer, 2015) [75] .  Turkey's GNSS-based navigation systems are an example of how developing nations prioritize core technology (Keskin et al., 2017) [67] .

Infrastructure

 Developed countries benefit from strong institutional support and infrastructure for technology adoption (Fountas et al., 2005) [41] .  Developing countries often lack the necessary infrastructure and technical training, slowing adoption rates (Verma, 2015) [146] .

Growth Potential

 Developed countries have mature markets with ongoing optimization and innovation (Robertson et al., 2012) [116] .  Developing countries, such as Brazil and China, show significant growth potential as they adopt new technologies (Bongiovanni & Lowenberg-DeBoer, 2005) [75] Fig

GPS (Global Positioning System)

For the precise determination of location in the crop field, two categories of interest emerged at that time, which we might think of as ideologies that influence field location decisions. A radiobased triangulation system with strategically positioned beacons was the initial concept. (Palmer,1991) [101] . The second idea was the GPS, which was in the late 1970s only used for military purposes (Tyler 1993; Larsen et al., 1988) [71,140] . The first idea had so many disadvantages like losing of signal during topography estimation, the amount of time needed to set up beacons in the field, place them, and modify their placements, among other things (Auernhammer and Muhr 1991) [10] . The second philosophy was a success but haslacked so many things that further improvement and changes occur in GPS. When the military began using GPS in the early 1990s, it could only achieve an accuracy of 3-5 meter using C/A code processing (Tyler 1993) [140] . A GPS receiver that is fixed in place is necessary for differential correction. When using a GPS receiver, a civilian user without the differential correction resource can only reach a range of 10-100 meters. Differential correction gained popularity in agriculture in the 2000s, after military selective availability was discontinued.

How a differential correction in GPS works?

A technique called differential correction is used to increase the accuracy of GPS signals by lowering errors brought on by satellite or atmospheric interference (Balaei and A. T., 2007) [12] . A ground-based reference station that offers real-time adjustments to GPS signals is the basis for the DC's operation (Dana and P. H., 1997) [28] . According to Yu et al. (2009) [158] , a fixed location is a ground-based reference station that continually receives GPS signals and computes precise locations based on satellite data. When the reference station's known location differs from its GPS-calculated position, the difference is referred to as an error signal (Han et al., 2001). GPS application in precision agriculture by field mapping, guidance system, variable Rate Technology (VRT), yield monitoring, and irrigation management.DGPS technology enhances the precision of agricultural operations, leading to improved efficiency, profitability, and sustainability.

The three components that make up GPS are as follows a) Satellites: which function similarly to stars in a constellation. b) Ground stations: Satellites are monitored and managed by ground stations. Additionally, ground stations pinpoint their position. c) Receivers: These devices are always on the lookout for satellite signals. Even the precise position may be determined within a fraction of an inch using highly sophisticated receivers. The satellite-based Global Positioning System works with a minimum of 24 satellites in the sphere. The satellites are positioned nearly 12,500 miles (20,000 km) fromthe level of the ground.These satellites do their work in any circumstances at 24*7 (Çelikbileket al., 2025).

Interesting GPS Facts

 The Decca Navigation System and LORAN served as the foundation for the initial concept of the Geo Positioning System. During World War II, both aided long-distance ship and aircraft navigation (Rankin and W,2014) [113] .  The United States owns 31 GPS satellites. Every twelve hours,  each GPS satellite completes a rotation of the planet (Kumar et al., 2002) [70] .

B. Geographical Information system (GIS)

A computer-based system is used for collecting, organizing, processing, and displaying the spatial data recognized as GIS. GIS helps to collect and combine the spatial information from several sources, such as satellite pictures, existing files, different sources, and databases. In the end, all the technology and methods it able to provide user assistance and help them to understand geographical information, patterns, trends, and correlations between the databases.

Components of GIS

 Hardware: Computers and devices used for processing and displaying geographic information.  Software: Tools that perform data analysis, visualization, and mapping.  Data: Spatial (location-based) and attribute (descriptive) data.  People: Users and analysts who interpret and apply GIS data.

 Methods: Processes and techniques for analysing geographic information effectively.

Applications of GIS in agriculture

GIS applications in agriculture include smart agriculture, crop monitoring with management, soil analysis, water resource management, yield prediction, climate impact assessment, land use planning, pest and disease management, supply chain optimization, and farm planning and development.

An image illustration of GIS in agriculture

C. Remote sensing technology

The science of collecting information on areas from a particular distance without physically making contact with the area. It is used to collect or gather information by using space technology to monitor earth's resources.

Components of Remote Sensing 1. Source of energy

The electromagnetic energy source, usually the Sun or a man-made source such as radar systems.

Atmosphere

The medium through which electromagnetic radiation travels. Atmospheric conditions may affect the transmission of energy.

Target (Object or Area)

The region or feature on Earth's surface that is being seen, including soil, plants, or bodies of water.

Sensor

The device that captures reflected or emitted radiation, often located on satellites, drones, or aircraft.

Data Transmission and Processing System 1.

Systems that process raw sensor data into interpretable formats, such as images, maps, or numerical data.

User Interpretation and Application:

Final analysis and application of the processed data for specific purposes, like agriculture, forestry, or urban planning. The major yield reduction in agriculture is caused by weed and their microclimate in crop fields. Weeds typically appear in patches across crop fields, and when their numbers get too large, they significantly reduce production and vigour (Coble and Mortensen 1992).Variable rate applications of pre-emergent or post-emergent herbicides were quite popular before the introduction of Roundup Ready crops (Wiles et al., 1992) [152] .To spray herbicides more effectively and at greater dosages in weed-dense regions, Thompson et al. (1990, 1991) [135] and Guyer et al. (1986) [53] proposed mapping weed sites using techniques like machine vision or remote sensing. Fields with recurrent weed patches benefited greatly from this, but real-time mapping was challenging since it was hard to tell weeds from crops. A spot sprayer that uses red and near-infrared reflectance to identify weeds was proposed by Felton and McCloy (1992) [38] . UAV and GPS technology were first used to target mapped weed areas in early work by Stafford and Miller (1993) [133] , but map-based systems were subsequently hampered by legal limitations. Real-time detection became the norm when Johnson et al. (1995) [63] found that weed patches were dynamic. Weed Seeker (1998) and machine vision technologies (1997-2002) are examples of sensor-based systems that have reduced the usage of herbicides by 63-85% and 66-80%, respectively. The effectiveness and sustainability of herbicide application were greatly improved by these improvements.

How Does Remote Sensing Work in

Variable rate irrigation

Another major problem of agriculture production is inadequate irrigation during different developmental stages of crops that leads to yield reduction and loss in plant vigour. The right amount and right time, along with the right method, help to maximize growth. The over irrigation leads to a water-logging situation along with nutrient leaching from surface runoff and insufficiency in irrigation, leading to drought. A technique utilizing centre pivot devices for variable rate irrigation (VRI) was patented by McCann and Stark (1993) [83] . They mapped irrigation zones on a microprocessor and utilized soil samples or aerial images to determine which zones need varying amounts of water. Then, they used solenoid valves to operate each nozzle. King et al. (1996) verified that this system successfully modified nitrogen and water applications.A comparable VRI system for linear irrigation was created by Fraisse (1994) [44] , and in South Carolina, center pivot systems with multiple manifolds were enhanced by Omary et al. (1997) and Camp et al. (1998) [99] to give up to eight water rates. A commercial farm was equipped with VRI controllers by Evans et al. (1996) [37] , who divided fields into 30 zones with two to four nozzles each. Using soil and climatic data, a potato growth model estimated water requirements. Despite its effectiveness, handling geographical data and wind-distorted spray patterns presented complications.

E. IoT (Internet of Things)

The need for food has grown dramatically due to the world's expanding population, making it difficult to produce enough food given the planet's finite resources. Precision Agriculture (PA) and other cutting-edge technology are being incorporated into farming methods to address this. PA uses near/remote sensing methods and Internet of Things (IoT) devices to track crops at different phases of development. It gathers and examines a great deal of information, such as temperature, insect presence, water levels, soil nutrients, and chlorophyll content. Based on current crop requirements, soil properties, and weather projections, farmers may use this information to make accurate agronomic decisions, such as the kind and quantity of fertilizer to use. A Wireless Sensor Network (WSN), which monitors environmental characteristics through networked wireless nodes, serves as the foundation of PA. Transceivers, microcontrollers, sensors, and antennae make up these nodes, which send data to a cloud system or gateway. The size and cost of sensors have decreased due to WSN improvements, making them suitable for widespread agricultural application. These sensors enable the monitoring of various crop needs that differ depending on the location and environmental circumstances. (wang et al., 2006) [148] . WSN applications include cyber-physical frameworks, which combine physical, software, and hardware elements to perceive and react to crop conditions (Abbasi et al., 2014) [2] . Potato crops have been monitored using such systems in three layers: decision (data analysis for actionable insights), network (data transmission), and physical (data gathering). Despite the exponential growth of connected devices, IoT-based agriculture confronts issues such as cloud congestion, latency, bandwidth limits, and sporadic internet access. Fog and edge computing are examples of emerging technologies that try to address these problems. By distributing computational work closer to the devices, fog computing improves service quality while saving energy and bandwidth. In simulations, a six-layer "Fog of Everything" (FOE) structure that incorporates virtualization and peer-to-peer communication has shown lower failure rates and more energy efficiency (Baccarelli et al., 2017) [33] . With the use of WSN and fog computing, IoT in agriculture has enormous potential to maximize resource utilization, boost yields, and sustainably satisfy future food demands.

Artificial intelligence of things (AIoT) in precision agriculture

Precision agriculture is important for maintaining and balancing global food production, which should be met towards global food demand. In recent decades, technical advancement in artificial intelligence with an association with the Internet of Things eradicates various constraints of crop production. AI and IoT-enabled applications are increasingly implemented for precision agriculture applications such as crop growth monitoring, weed removal control, pest and disease detection, planting, crop yield estimation, targeted spraying and pollination, smart irrigation and nutrient management, field analysis, and plant phenoltyping. IoT-based applications that employ machine learning and deep learning models, for instance, are frequently used to evaluate soil quality and nutrients as well as identify fruits, vegetables, weeds, pests, and illnesses. Such data aids in improving crop management techniques. A combination of two precise technologies as IOT and AI preferred as AIOT. AIOT is still at the stage of research stage and needs more development. And faces many more struggle and obstacles to work, like data collection errors, unable to catch ai algorithms, can't process sources or data also unable to process computing capabilities.

F. Yield Mapping

Making spatial maps of the variations in agricultural production across fields is known as yield mapping. Originally developed by Schueller and Bae (1987) [126] , before GPS, early techniques employed microwave range for locating and engine speed to estimate grain flow. However, inaccuracies due to wheel slippage prompted advancements like grain auger volume measurements (Bae et al., 1987; Searcy et al., 1989) [126] . Modern systems, such as deflection-based grain flow monitors (Vanischen &Baerdemaeker, 1991), enhance precision by mitigating signal distortion. Errors in yield mapping-like swath overlap and turnaround inaccuracies-can be reduced using centimeter-accuracy GPS systems (Pierce et al., 1997). Soil factors, such as depth to argillic horizon, elevation, and organic matter, significantly affect crop yield variability (Karlen et al., 1990; Sudduth et al., 1996) [65] . Temporal factors, including precipitation, also play a role, with year-to-year variations often surpassing spatial ones (McBratney & Whelan, 1999) [82] . Spatial yield maps often fail to predict future variability accurately. Lamb et al. 1997 demonstrated that past spatial yield patterns could explain only half the variability in subsequent years. Similarly, according to Blackmore et al. (2003) [43] , yield variability varies from year to year., emphasizing in-year management over historical patterns. A crucial distinction lies in yield versus crop response. The name drone at the beginning of drone exploration is linked to or, we can say taken from drone bee from honeybee colony. The link is likely the drone bees' work by taking the command from queen bees without making their own decisions, so drone function is mainly like that a command-based programme is incorporated to the drone and it is controlled by a remote in that all the functional aspects are present so that a person without physically controlled the machine can operated from a specific direction or distance. The machine in the early era of precision farming was called an unmanned aerial vehicle because it operated without any pilot (Joiner, 2018).

Types of Drones

In the world of technology, where drones are sold, they offer a wide variety or range of drones from considering factors including physical features, purpose of drone usage, range of their flight, and weight of the drone (Joiner, 2018) Table 3: Drone categorization based on flight range and weight (Hassanalian and Abdelkefi, 2017) [56] Types 15. Sorting and Grading: Arranging fruits and vegetables according to their size and quality.

Managing orchards with precision agriculture

Precision agriculture in fruit crops aims to increase economic efficiency and production by managing each site differently. To address physical, biological, and chemical aspects and lessen environmental consequences while enhancing agricultural outcomes, key activities include data collecting, identifying orchard variability, and making well-informed choices (Zhang & Kovacs, 2012) [55] .

Effective fruit crop management involves key practices like thinning, pruning, and irrigation to improve fruit size, quality, and yield. [141] Recent studies that analyse data from several platforms have shown how effective it is in managing orchards (Barbagallo et al., 2009; Garcia-Ruiz et al., 2013 [46] ; Salgadoe et al., 2018). Manual observation (MO), handheld detection (HD), sensor networks (SN), ground vehicles (GV), unmanned aerial vehicles (UAVs), aerial sensing (AS), and spectral satellite sensing (SSS) are among the methods that are suitable for specific orchard management tasks such as yield prediction, disease detection, thinning, and spraying throughout the fruit tree growth cycle. UAVs are becoming more and more useful for real-time orchard monitoring at appropriate geographical, spectral, and temporal resolutions, thanks to recent developments in sensor downsizing (Berni et al., 2009 [14] ; Caruso et al., 2019 [24] ; Torres-Sanchez et al., 2018; Valente et al., 2019) [136] . Equipped with thermal sensors, multispectral sensors, and LiDAR systems, UAVs offer advantages over ground-based platforms, including portability and real-time field map generation, as well as over satellitebased remote sensing, having greater data-acquisition probabilities in cloudy areas and being less weather-dependent (Campos et al. [22] , 2019; Matese et al., 2019 [81] ; van der Wal et al., 2013) [143] . Additionally, UAVs may be used in high-risk situations, produce geo-referenced photos, and offer quick data collection (Handique et al., 2017 [54] ; Saldana Ochoa & Guo, 2019) [121] . Effective monitoring of small to medium-sized orchards is ensured by striking an ideal balance between flying speed and data quality, despite limits in battery life and operational speed as compared to manned platforms (Garcia-Ruiz et al., 2013) [46] .

UAV and unmanned aerial vehicles' role In orchard management practices

The restrictions and needs of the application determine the type of UAV to use for orchard management. The most popular UAVs in orchards are multi-rotor models, which have benefits like hovering, GPS-based navigation, vertical and horizontal flying, and small-space operation. They are easy to control and provide high maneuverability, with optical sensors achieving centimetre-level 3D resolution at a 70 m altitude (Caruso et al., 2019) [24] . However, they have shorter flight times and slower speeds compared to fixed-wing UAVs, which offer longer flight durations, faster speeds, and higher payload capacities but lack hovering capability and may cause image blurring, addressable with fast-shutter imaging sensors.

Different types of sensors equipped in UAVs:

Although they have shown promise in orchard management, the five sensor types utilized in UAVs-RGB, thermal, multispectral, hyperspectral, and LiDAR-have several drawbacks (Díaz-Varela et al. [30] , 2015; Tu et al., 2018). Hyperspectral sensors, while capable of high spatial resolution, are limited by size, cost, and geometric calibration issues, affecting their adoption (Vanbrabant et al., 2019) [144] . LiDAR, though promising for geometric trait measurement, remains largely unexplored in this domain (Díaz-Varela et al., 2015) [30] . RGB sensors lack essential camera and radiometric calibration, reducing accuracy, particularly in geometric estimations (Tu et al., 2018). Multi-modal sensing, which integrates different sensors on the same UAV, offers the potential to improve detection accuracy by combining unique data traits (Kesturet al., 2018). To get compaction and compatibility and size reduction, these features are needed to implement in sensors to retrieve benefits. (Hadas et al., 2019) [51] , To retrieve high-quality pictures, extraction of qualitative and quantitative data, and sensor-based drones, these features are needed for sensor development. (Vanbrabant et al., 2019) [144] .

Fig 11:

The figure's vibrantly coloured circles' regions show the percentage employed in comparable applications; rounded rectangles stand for zero, and a certain number of pertinent items are also indicated. "G" stands for geometric and biophysical characteristics (light blue), "P" for productivity applications (yellow), "D" for disease detection (orange), "O" for other applications (green), and "R" for resource efficiency in orchards (dark blue). These acronyms are the category of application initials.

Observation and Monitoring

Stress indicators like illnesses, pests, water scarcity, or nutritional shortages can be detected by UAVs fitted with thermal and multispectral sensors (Zhang & Kovacs, 2012) [55] . Additionally, they offer aerial photography to measure canopy uniformity and density, which aids in assessing the general health and production of trees (Torres-Sánchez et al., 2014) [136] . Timely treatments that minimize potential losses are ensured by early diagnosis of issues such as fungal infections, insect infestations, or mechanical damage (Zhang & Kovacs, 2012) [55] .

Accurate Use

UAVs with sprayer attachments can be used to apply fertilizer and pesticides, reducing waste and adverse environmental consequences (Sinha et al., 2020) [130] . Targeted distribution boosts efficiency and ensures successful applications even in hard-to-reach orchard areas (Hunt et al., 2013) [59] .

Data Collection and Analysis

The high-resolution image of fruits, fruit size, color, and harvesting indices are needed to be input in UAV programmes (Torres et al., 2014) [136] . For proper orchard management, the integrated collected and retrieved data from drones with respect to the GIS functions help in making productive maps for effective orchard management (Hunt et al., 2013) [59] .

Environmental Monitoring:

Sensor-based drones capture parameters like temperature, humidity, photoperiod, and wetness, which helps to gather information to ensure strategies to measure plant protection and irrigation that estimate microclimate data (Hunt et al., 2013) [59] . To estimate water requirement for crop cultivation, like efficiency of water along with scheduling irrigation soil mapping needed through which soil moisture mapping is done (Hunt et al., 2013) [59] .

Pollination Support

UAVs can monitor and document pollinator activity, helping evaluate pollination efficiency and coverage within orchards (Zhang & Kovacs, 2012) [55] .

Labour Efficiency and Cost

Numerous orchard chores are automated by UAVs, which minimizes reliance on manual labour and permits resource optimization (Sinha et al., 2020) [130] . Long-term cost savings are achieved by early issue detection and effective resource use (Torres-Sánchez et al., 2014) [136] .

Remote sensing application in horticulture

Interestingly, India is one of the few countries using land-based observations and satellite technologies for sustainable agricultural operations, including horticulture. In a 1970 coconut withering experiment in India, remote sensing was initially used (Ray, 2016) [114] . For uses including crop production estimation, precision farming, drought monitoring, and climate impact assessment, Indian academics have refined digital image processing and created proprietary software since then (Navalgund and Ray, 2000 [94] ; Panigrahi and Ray, 2006; Navalgund et al., 2007) [95] . ISRO and other organizations have implemented projects that have institutionalized these techniques in agriculture (Parihar and Manjunath, 2013) [103] .

Key application of remote sensing in Horticulture

 Crop Insurance: By validating planted crops, satellite data (NDVI) helps lower insurance fraud.  Monitoring Soil Moisture: Soil moisture is measured using both active and passive sensors, which is essential for weather forecasting and drought analysis.  Crop Health and Yield Estimation: (Hao et al., 2011 [55] ;

Jensen, 2000 [62] ; Usha et al., 2013) [41] NDVI and multispectral photography evaluate crop health, forecast yields, and distinguish horticulture crops from other vegetation.  Early detection of pest and disease outbreaks can be facilitated by variations in reflectance in stressed plants (Johnson et al., 1996) [63] .  Abiotic Stress Monitoring: Chlorophyll variations brought on by stress can be identified using reflectance data (Usha et al., 2013) [41] .

Precision spraying systems for fruit trees

Lowering the risk of pesticide use is one of the primary challenges that harms the ecology, the environment, and human health. By providing the right amount and dose at the target area, the precision spraying system is one of the most efficient technical solutions for pesticide administration, preventing overuse and toxicity (Oerke et al., 1994) [98] . This is necessary to sustain insect infestation and pest population. Since crop losses of up to 100% can result from the improper management of insects, pests, diseases, and weeds, fruits depend on pesticides for reliable production. However, because pesticides can pollute soil, groundwater, and air, endangering the environment, human health, and animal welfare, their usage in orchards has come under fire. Furthermore, tree fruit producers must pay hundreds to thousands of euro's per hectare for pesticides, which accounts for around one-third of overall production costs (Weinzierl et al., 2015) [151] . Most pesticide waste comes from applications to the spaces above, under, and between tree canopies. Pesticide waste and usage may be significantly reduced by carefully and selectively applying pesticides to tree canopies.

What is Precision Spraying?

Precision spraying involves applying pesticides or other chemicals only where and when they are needed, using technologies like sensors and GPS to optimize application rates and minimize waste. For instance, Esau et al. (2014) [36] were able to reduce agrochemical use from 9.90% to 51.22% by using precision spraying technology to avoid applying pesticides to bare spot areas in wild blueberry fields. Despite improvements, precision spraying in tree fruit orchards still confronts obstacles such as drift, chemical loss, and limited large-scale viability. The camera, ultrasonic, and laser sensing technologies that are currently in use are restricted and have poor real-time performance. Nozzle type, spraying distance, droplet size, canopy structure, wind, temperature, and humidity are the important parameters in precision spraying. Future work should focus on bridging technological gaps to spray orchards effectively and efficiently.

Chemical Sprayers in Tree Fruit Orchards Evolution of Sprayer Technology

 Early designs included hand-boom, horse-drawn wagons, and steam-powered sprayers (Lodeman et al., 1916) [73] .  Air blast sprayers gained popularity in the 1940s due to labour shortages (Potts and S.F., 1946) [107] .  Innovations like mist blowers and handguns allowed efficient pesticide application (Fleming, G.A, 1962) [40] .

Modern Sprayer Designs

 Air Jet Models: Enabled ground-based spraying into tree canopies (Randall and J.M,1971) [112] .  Air Blast Sprayers: Axial-fan sprayers, suitable for older orchards with large canopies, face limitations with smaller, modern orchards (Fox et al., 2008&Cross and Patternation,1991) [43,27] .  Tower and Tunnel Sprayers: They improve canopy coverage but have high costs and limited adaptability (Chen and Y, 2010).  Precision Sprayers: Sensor-guided systems reduce chemical use and off-target deposition (Boatwright et al., 2020) [17] .

Challenges with Conventional Sprayers

 Older sprayers waste up to 50-70% of pesticides due to inefficient matching with modern orchard tree sizes (Brown et al., 2008).

 Conventional broadcast spraying fails to adjust for variables like weather, tree density, or missing trees, leading to significant losses (Edward,2001)

Precision Spraying Benefits  Uses real-time canopy data to optimize pesticide application, reducing wastage and environmental contamination. (Chen and Y, 2010 and Boatwright et al., 2020) [17] .

The technological development of sprayers for orchard spraying

Category

Sprayer Types References

Accurate Sprayers Intelligent sprayers and sensor-guided air blasters Ludeman and E.G,1916 [107] Fleming, G.A, 1962 [40] Contemporary Air Blast Sprayers Tunnel sprayers and tower sprayers Randalland J.M,1971 [112] Travis et al., 1987 [137] Fox et al., 1992 [42] Models of air jets Plane jet sprayers and polar jets Peterson et al., 1994 Walklate et al.., 2000 [147] Designs of Early Sprayer Handguns, early mist blowers, boom sprayers, and steam-powered sprayers [Ludeman and E.G,1916 [107] Rose and G.E., 1955 Fleming, G.A, 1962 [40] Fig 12: (A) Constant rate air blast sprayer system (B) Precision spraying system AI in Horticulture India's unique soils, temperatures thereby and agro-ecological zones promote the development of a broad spectrum of horticulture crops, which boost the economy through raising productivity, creating jobs, and providing raw materials for food processing. By using AI in horticulture, high demand may be satisfied despite a lack of land. AI helps with weather forecasting, irrigation optimization, disease diagnosis, pest management, yield forecasting, harvesting automation, postharvest loss reduction, and fruit quality improvement for processing organizations. Strong mathematical methods and programming tools are used to create artificial intelligence. American computer scientist John McCarthy initially proposed it in 1956.Models of artificial intelligence (AI) and machine learning (ML) evaluate agricultural data, such as weather, soil, and water use, to maximize planting, irrigation, harvesting, and pest management. The food supply chain, crop health, and resource management are all improved by these technologies, which also provide customized solutions and boost productivity and product quality.

Utilizing AI to Forecast Soil Fertility

Crop health depends on critical elements, including soil nutrients, pH, moisture, and temperature, but they are presently measured with labour-intensive techniques. By actively monitoring soil conditions, AI technologies like drones, unmanned aerial vehicles, and computer vision models simplify these procedures. By connecting leaf patterns to soil flaws, tools such as Plantix by PEAT, a deep learning program, may detect nutrient deficits (Varshitha and Choudhary, 2021) [145] . An ANN-based system was created by (Palaniappan et al. 2019) [100] to analyze soil characteristics and suggest appropriate crops.

AI in Crop Production

By anticipating environmental changes and facilitating prompt responses, like early harvests, AI tackles issues like temperature rises and frost events. As evidenced by Sentiment's methods for maximizing basil growth, greenhouse applications involve automated monitoring and management of environmental parameters (Sahni et al., 2021) [119] . Using meteorological data, neural network models, such as those developed by Robinson and Mort (1997) [117] , can reliably forecast frost. Srbinovska et al. (2014) [132] and Qiu et al. ( 2014) [110] developed sophisticated systems that automate greenhouse conditions for the best agricultural yield.

Application of AI in Assisting Pollination

Shrinking natural pollinator populations threaten food supply, and AI solutions are emerging to assist pollination. Monash University used AI and computer vision to track pollinator species, enhancing strawberry crop yields. Chen and Li (2016) developed robotic micro-air vehicles for autonomous pollination, employing real-time field data and thermal sensors to optimize the process.

Application of AI in Automated Irrigation

By automating processes based on current environmental and soil moisture data, artificial intelligence (AI) improves irrigation efficiency. Technologies that improve water utilization include electro tensiometers for demand-based fertigation (Contreras et al., 2021) [26] and soil sense by Proximal Soil Sens Technologies Pt. Ltd., which offers irrigation guidance through mobile applications (Manaware, 2020) [80] . By measuring trunk variations and water status, respectively, dendrometers and drone-mounted cameras enhance irrigation even more (Santesteban et al., 2016; Hahn et al., 2021) [53,124] .

AI's Use in Crop Phenotype Determination

AI replaces labour-intensive conventional approaches by streamlining the collection of phenotypic data for breeding techniques. With 99.9% tree count accuracy, Ampatzidis et al.

(2019) [9] showed that UAVs with sensors can efficiently track phenotypic changes in citrus rootstocks. Apple tree crown features are analyzed using deep learning models, such as those employed by Wu et al. (2020) [153] , which help with growth monitoring, machine harvesting, and precision spraying.

Application of AI in Disease Diagnosis

Plant diseases cause up to 40% of global crop losses (Fenu and Malloci, 2021) [39] . AI-driven systems enhance early disease detection and treatment, improving yield. Examples include drone-based vegetation indices for disease mapping (Patel et al., 2013) [104] , grape vineyard monitoring using sensors (Patil and Thorat, 2016) [105] , and smartphone-assisted illness diagnosis with 99.35% accuracy (Mohanty et al., 2016) [86] . Deep learning systems like Plantix diagnose plant diseases with 95% accuracy (Manaware, 2020) [80] .

AI in Field Management

AI optimizes pesticide application, lowering labour and chemical use; UAVs with pre-mapped routes improve spraying efficiency; robots such as "See & Spray" use computer vision for targeted weed spraying, saving 90% of herbicide (Bhavana and Bhagwan, 2021) [15] ; and autonomous systems such as Agrobot Srishti use sophisticated algorithms to identify and remove weeds (Debnath, 2020) [29] .

Application of AI in Produce Maturity Identification

AI guarantees accurate ripeness evaluation for the best crop. Systems that use ANN and computer vision, such as Yossy et al.

(2017) [157] , can classify mango ripeness with 94% accuracy. For determining the maturity of crops, including apples ( [8] , methods like RGB image processing forecast orange sweetness based on red color intensity, and NIR spectrophotometry determines the amount of sugar in grapes (Gutierrez et al., 2018) [49] . 9. Application of AI in Yield Forecasting AI reduces manual labor and time by enabling accurate production predictions through automated fruit-counting systems. To increase productivity, systems employing deep learning and image processing architectures recognize and count fruits for harvest planning and yield estimate (Lomte et al., 2019; Maheswari et al., 2021) [74,78] .

AI in Harvesting

AI-driven harvesting robots help reduce labor shortages and expenses. With the use of cameras and sensors, these robots can differentiate between fruits and leaves, select fruits with the least amount of damage, and use sophisticated path-planning algorithms for effective operations (Kitamura et al., 2005; Xiong et al., 2020). High-value crops are handled delicately, thanks to robotic systems like Vegebot and soft grippers (Navas et al., 2021; Birrell et al., 2019) [69,154] .

Application of AI in Fruit Grading

AI-based grading systems leverage computer vision and fuzzy logic to classify and grade fruits with high accuracy. Image processing techniques extract features like size and shape, while machine vision systems reduce human errors and ensure consistent quality (Kavdir & Guyer, 2003; Mustafa et al., 2009) [66, 91] . Advanced systems like TOMRA sorting machines use AI to enhance sorting and grading efficiency (Sahni et al., 2021) [119] .

12. Using AI to Reduce Postharvest Losses AI may be used to reduce post-harvest losses brought on by microbial infections, bruising, and moisture loss. To ensure longer shelf life and less spoiling, hyperspectral imaging and neural networks identify interior damage, improve storage conditions, and forecast deterioration risks (Morimoto et al., 1997; Nagata et al., 2006) [89,92] .

Application of AI in Quality Assessment

AI enables non-destructive quality assessment by analyzing parameters like moisture, pH, and spoilage. Techniques like image classification, electronic noses, and sensor-based systems identify defects and predict shelf life accurately. These advancements improve product safety and consumer satisfaction (Sanaeifar et al., 2014; Megalingam et al., 2019) [123,111] .

AI application in Processing Industry

AI streamlines food processing with self-optimizing cleaning systems and augmented vision sensors. These systems detect residues, optimize cleaning resources, and ensure only suitable products enter the processing line, improving efficiency and hygiene (Sahni et al., 2021) [119] .

Application of AI in Aeroponics

AI-driven aeroponic systems employ sensors to monitor temperature, humidity, pH, and water levels. Real-time data comparison and alerts through mobile applications help maintain optimal growth conditions, promoting sustainable farming (Priyanka et al., 2020).

AI types used in the agriculture sector (Dotaniya et al.,

2024) [32] The AI types or their classification is based on the complexity level, and another classification is based on the functionality level.

a) Strong artificial intelligence and weak artificial intelligence are the two major components of complexity-classified AI. By their name, we can calculate their level of potential compared to the intelligence of humans.

Applications of Remote Sensing in Horticulture

India is home to a variety of crops, and remote sensing is crucial to measure these crop data by properly utilizing satellite technology and integrated technology of ground-based stations (Ray, 2016) [114] . In 1970, a coconut withering experiment in India was the first known application of remote sensing. Since then, the development of proprietary software and improvements in digital image processing have been greatly aided by Indian researchers (Navalgund and Ray, 2000 [94] ; Panigrahi and Ray, 2006) [95] . Precision farming, crop acreage estimation, agricultural water management, drought monitoring, and watershed development are some of the horticultural uses of remote sensing (Parihar and Manjunath, 2013) [103] . Many of these techniques, tested in practical field conditions, are now institutionalized.

Key Applications 1. Crop Insurance: Remote sensing, using satellite imagery and NDVI (Normalized Difference Vegetation Index), helps verify seeded crops and prevent insurance fraud (GIS Geography).

Soil Moisture:

Soil moisture is measured using both active and passive sensors, which is crucial for drought evaluation and weather forecasting. NASA's Soil Moisture Active Passive (SMAP) research employs both strategies for optimal outcomes (GIS Geography).

Crop Conditions and Canopy Measurement:

NDVI is employed to assess crop health, chlorophyll content, and canopy water stress. This method also predicts soil properties and aids in managing crop canopies (Smart et al., 2000; Schumann, 2008) [127] .

Yield Estimation:

Remote sensing enables yield predictions for annual crops and some horticultural crops using aerial imagery and spectral indices (Maja and Ehsani, 2010) [79] . [119] .

Monitoring Abiotic Stress:

By tracking variations in chlorophyll reflectance, remote sensing methods identify how plants react to abiotic stressors such as drought, salt, and temperature swings (Carter, 1993) [23] .

Machine learning

To meet the food demand for fulfilling the growing population, the 4 th wave of revolution now begins that is towards the digital revolution with precision farming composing IoT, ML, satellite technology, and artificial intelligence (Saini et al., 2024) [120] .

History of Machine Learning

A science or technology that implements or provides an ability to the computer to learn and expand its knowledge without being programmed. In simpler the computer has its ability to learn new pieces of knowledge without any program (Arthur Samuel, 1959). The turning test for machine intelligence is a research paper written and published by Alan Turing in the early to mid of. 1950, in this paper, he proposes the major concepts of machine learning (Alan Turing, 2009).36 ML techniques, considering a total of 80 implementations from which NN, RF, SVM, and DT were the most frequently implemented.



The process of ML has three components which are generalization, data imputation and the last one is model building.  According to the task of learning, machine learning has two types, i.e., supervised and unsupervised learning.

Supervised learning:

There is a general guideline with the corresponding rule provided so that the maps, data input, and output interpretation are easily done because, in supervised learning, some data and their example are pre-programmed.

Unsupervised learning:

Previously, in supervised learning, the machine was trained and tested, but in this type of machine learning, there is no such data, training, or testing, and preprogrammed data are not provided. This type of distinction is absent here. The learner has the goal to set by inputting data here to discover some hidden features or patterns.

Machine learning in precision agriculture

The data or information called big data needs large storage and also the capability of editing, interpreting, and analysing that has given challenges to the users of precision tools, but with the help of AI and the body of machine learning it is possible to manage and manipulate such larger amounts of knowledge or information or can say data (Helm et al., 2020) [58] . The incorporation of precision tools with machine learning is a primordial factor in the development of a bright future in food production. AI, sensors, drones, GIS, GPS, and monitoring systems are helpful for machine learning to estimate, calculate, interpret, and process the input information and also helpful for identifying key problems, timely management, and some hidden beneficial factors. Towards reducing labour drones and robots are enabled in fields (A. Sharma et al., 2021). Prediction of harvesting and yield, detection of pest and disease infestation, detection and interpretation of data about the weed microclimate in crop fields, and identification and recognition of crops and quality attributes of crop are the four major parts or sectors of agriculture that are explored by machine learning. In machine learning, there is a networking system called an artificial neural network, and its processing factor is similar to the human brain processing system, and like the brain neural, once it is trained according to a similar pattern, in the future, it predicts, solves complex problems into simpler solutions and ANN accuracy of problem solving has increases with addition of more data to it (Mishra et al., 2016) [85] Problems in the use of machine learning Wang et al. identified challenges in four stages of agricultural Big Data, including multiple data sources, low precision, slow processing, long collection times, high complexity, and missing data. The key focus areas are data cleaning, consolidation, and storage (Wang et al., 2019) [149] . The programming of machine learning varies from different to organization, so the problem is that the data is malfunctioning and changes when it goes from one organization to another. The results are greatly varying, and it happens due to different hardware used for data collection (Priya and Ramesh, 2020) [108] . On the other hand, another challenge raised was the velocity or speed with which data is collected, but processing and visualization can't proceed with that speed (Priya et al., 2018) [109] .

Limitations of precision farming 25-30 years above the precision farming used in the agriculture sector and its precise use to maximize production, obtaining maximum output, towards reducing the negative environmental impacts. The fact remains that after implementing precision agriculture then people still choose traditional methods of farming. People always show the positive side of things, but they forget to bring up the negative side of things. In developing countries like India because people still choose traditional methods of farming because, in India-like countries, farmers are unaware of the smart farming methods because of the lack of extension services of precision farming, low land area for farmers, high cost of precision farming tools, lack of government schemes and the lack of funding towards precision farming implementations. In comparison to developed countries, they lack manpower, so it's easier for their people to adapt and implement precision farming tools in day-to-day life, but in developing countries, there is not lack of manpower and due to high cost of implementing precision tools it's still a drawback towards adoption of precision farming.

Conclusion

According to the global crisis that is referred to as climate change and growing population, the need of food demand and farming practices precision farming principle and components are the major beneficial factor to mitigate these problems arise. To maximize production, generate higher profit, increase the amount of yield, and maintain a healthy relationship between humans and the environment, these majors are necessary. The GIS, GPS, remote sensing, drone, AI, sensors, and Machine learning are the networks that change the perspective of farming technology. But still, the developing countries are lacking in adopting the smart technology than the developed countries much more emphazisation is still needs to develop the farming style in developing countries. These countries lack in adoption due to the higher cost of the tools like drones, sensors, AI, and also the government schemes and benefits. They are unaware that these much more awareness should spread among farmers and people. It brings a major impact in horticulture. The ongoing development of digital technology and its use in horticulture portend a bright future for precision farming, supporting a robust and creative agricultural industry. Enhancing these technologies' cost and accessibility, guaranteeing their widespread use and future research should focus on developing algorithms for even greater accuracy and efficiency (Zhang et al., 2021).

References

1. harma A, Jain A, Gupta P, Chowdary V. Machine Learning Applications for Precision Agriculture: A Comprehensive Review. IEEE Access. 2021;9:4843-4873. doi:10.1109/ACCESS.2020.3048415.
2. Abbasi AZ, Islam N, Shaikh ZA. A review of wireless sensors and networks' applications in agriculture. Comput Stand Interfaces. 2014;36(2):263-270. doi:10.1016/j.csi.2011.03.004.
3. Adinarayana S, Raju MG, Srirangam DP, Prasad DS, Kumar MR, Veesam SB. Enhancing Resource Management in Precision Farming through AI-Based Irrigation Optimization. In: How Machine Learning is Innovating Today's World: A Concise Technical Guide. 2024:221-251. doi:10.1002/9781394214167.ch15.
4. Ahmad L, Mahdi SS, Ahmad L, Mahdi SS. Components of precision agriculture. In: Satellite Farming: An Information and Technology Based Agriculture. 2018:19-30. doi:10.1007/978-3-030-03448-12.
5. Ahmad SF, Dar AH. Precision farming for resource use efficiency. In: Resources Use Efficiency in Agriculture. 2020:109-135. doi:10.1007/978-981-15-6953-1_4.
6. Akdemir B. Evolution of precision farming research and applications in Turkey. In: Proceedings of the VII International Scientific Agriculture Symposium "Agrosym 2016". Jahorina, Bosnia and Herzegovina. 2016:1498-1504.
7. Allen R. Agriculture during the industrial revolution. The Economic History of Britain Since 1700. 1994;3:96-123.
8. Al-Sammarraie MAJ, Gierz Ł, Przybył K, Koszela K, Szychta M, Brzykcy J, Baranowska HM. Predicting fruit's sweetness using artificial intelligence-case study: Orange. Appl Sci. 2022;12(16):8233. doi:10.3390/app12168233.
9. Ampatzidis Y, Partel V, Meyering B, Albrecht U. Citrus rootstock evaluation utilizing UAV-based remote sensing and artificial intelligence. Comput Electron Agric. 2019;164:104900. doi:10.1016/j.compag.2019.104900.
10. Auernhammer H, Muhr T. GPS in a basic rule for environment protection in agriculture. In: Kranzler G, editor. Automated Agriculture for the 21st Century. ASAE Publ. 1991:394-402.
11. Avtar R, Watanabe T, editors. Unmanned aerial vehicle: Applications in agriculture and environment. Cham, Switzerland: Springer International Publishing; 2020. doi:10.1007/978-3-030-27157-2.
12. Balaei AT. Detection, characterization, and mitigation of interference in receivers for global navigation satellite systems. [PhD Thesis]. University of New South Wales; 2007.
13. Beluhova-Uzunova RP, Dunchev DM. Precision farmingconcepts and perspectives. Zagadnienia Ekonomiki Rolnej. 2019;(3). doi:10.30858/zer/112132.
14. Berni JAJ, Zarco-Tejada PJ, Sepulcre-Canto G, Fereres E, Villalobos F. Mapping canopy conductance and CWSI in olive orchards using high-resolution thermal remote sensing imagery. Remote Sens Environ. 2009;113(6):1330-1340. doi:10.1016/j.rse.2009.06.018.
15. Bhavana H, Bhagwan A. Review on: Role of robotics in horticulture. J Pharmacogn Phytochem. 2021;10(1):306309.
16. Birrell S, Hughes J, Cai JY, Iida F. A field-tested robotic harvesting system for iceberg lettuce. J Field Robotics. 2019;37(2):1-21. doi:10.1002/rob.21888.
17. Boatwright H, Zhu H, Clark A, Schnabel G. Evaluation of the intelligent sprayer system in peach production. Plant Dis. 2020;104:3207-3212. doi:10.1094/PDIS-04-20-0696RE.
18. Bongiovanni R, Lowenberg-DeBoer J. Precision agriculture in Argentina. In: Proceedings of the 3rd Simpósio Internacional de Agricultura de Precisão. EMBRAPA, Brazil; 2005.
19. Borengasser M, Gottwald TR, Riley T. Spectral reflectance of citrus canker. In: Proceedings of the Florida State Horticultural Society. 2001;114:77-79.
20. Borghi E, Avanzi JC, Bortolon L, Luchiari Junior A, Bortolon ESO. Adoption and use of precision agriculture in Brazil: Perception of growers and service dealership. J Agric Sci. 2016;8(11):89-104. doi:10.5539/jas.v8n11p89.
21. Camp CR, Sadler EJ, Evans DE, Usrey LJ, Omary M. Modified centre pivot system for precision management of water and nutrients. Appl Eng Agric. 1998;14(1):23-32. doi:10.13031/2013.19362.
22. Campos J, Llop J, Gallart M, et al. Development of canopy vigour maps using UAV for site-specific management during the vineyard spraying process. Precision Agric. 2019;20:1136-1156. doi:10.1007/s11119-019-09643-z.
23. Caruso G, Zarco-Tejada PJ, González-Dugo V, Moriondo M, Tozzini L, Palai G, et al. High-resolution imagery acquired from an unmanned platform to estimate biophysical and geometrical parameters of olive trees under different irrigation regimes. PLoS ONE. 2019;14(1):e0210804. doi:10.1371/j
24. Coble HD, Mortensen DA. The threshold concept and its application to weed science. Weed Technol. 1992;6(1):1915. doi:10.1017/S0890037X00034552.
25. Contreras JI, Baeza R, Lopez JG, Canovas G, Alonso F. Management of fertigation in horticultural crops through automation with electrotensiometers: Effect on the productivity of water and nutrients. Sensors. 2021;21:190. doi:10.3390/s21010190.
26. Cross JV. Pattern of spray mass flux from axial fan air blast sprayers in the orchard. Br Crop Prot Counc Monogr. 1991;46:15-22.
27. Dana PH. Global positioning system (GPS) time dissemination for real-time applications. Real-Time Syst. 1997;12:9-40. doi:10.1023/A:1007906014916.
28. Debnath D. Autonomous agriculture robot -Agrobot Srishti. Int J Res Appl Sci Eng Technol. 2020;8(6):217-27.
29. Díaz-Varela R, de la Rosa R, León L, Zarco-Tejada P. High-resolution airborne UAV imagery to assess olive tree crown parameters using 3D photo reconstruction: Application in breeding trials. Remote Sens. 2015;7(4):4213-32. doi:10.3390/rs70404213.
30. Doerge T. Defining management zones for precision farming. Crop Insights. 1999;8(21):1-5.
31. Dotaniya ML, Kumar K, Dotaniya CK, et al. Role of artificial intelligence in natural resource management. Biotica Res Today. 2024;6(8):410-3.
32. Baccarelli E, Naranjo PGV, Scarpiniti M, Shojafar M, Abawajy JH. Fog of everything: Energy-efficient networked computing architectures, research challenges, and a case study. IEEE Access. 2017;5:9882-910. doi:10.1109/ACCESS.2017.2702013.
33. Emenonye DR, Dhillon HS, Buehrer RM. Geolocation with large LEO constellations: Insights from Fisher Information. arXiv preprint arXiv:2502.06083. 2025. doi:10.48550/arXiv.2502.06083.
34. Erickson B, Widmar DA. 2015 Precision agricultural services dealership survey results. Purdue University. West Lafayette, Indiana, USA. 2015. 37 pp.
35. Esau TJ, Zaman QU, Chang YK, et al. Spot-application of fungicide for wild blueberry using an automated prototype variable rate sprayer. Precision Agric. 2014;15:147-61. doi:10.1007/s11119-013-9319-4.
36. Evans RG, Han S, Kroeger MW, Schneider SM. Precision center pivot irrigation for efficient use of water and nitrogen. In: Robert PC, Rust RH, Larson WE, editors. Precision Agriculture: Proceedings of the 3rd Intl. Conf. ASA-CSSA-SSSA; 1996; Madison, WI. p. 75-84. doi:10.2134/1996.precisionagproc3.c8.
37. Felton W, McCloy K. Controller for agricultural sprays. U.S. Patent No. 5,144,767. 1992 Sep 8.
38. Fenu G, Malloci FM. Forecasting plant and crop disease: An explorative study on current algorithms. Big Data Cogn Comput. 2021;5(2):1-24. doi:10.3390/bdcc5010002.
39. Fleming GA. The relationship of air volume, air velocity, and droplet size to the efficiency of spray transport in airblast spraying. PhD Thesis, Cornell University, Ithaca, NY, USA. 1962.
40. Fox RD, Brazee RD, Svensson SA, Reichard DL. Air jet velocities from a cross-flow fan sprayer. Trans ASAE. 1992;35:1381-4. doi:10.13031/2013.28744.
41. Fox RD, Derksen RC, Zhu H, Brazee RD, Svensson SA. A history of air-blast sprayer development and prospects. Trans ASABE. 2008;51:405-10. doi:10.13031/2013.24375.
42. Fraisse CW. Variable water application with moving irrigation systems. PhD dissertation, Colorado State University, Ft. Collins, CO. 1994.
43. Gao P, Zhang Y, Zhang L, Noguchi R, Ahamed T. Development of a recognition system for spraying areas from unmanned aerial vehicles using a machine learning approach. Sensors (Basel). 2019;19(2):313. doi:10.3390/s19020313.
44. Garcia-Ruiz F, Sankaran S, Maja JM, Lee WS, Rasmussen J, Ehsani R. Comparison of two aerial imaging platforms for identification of Huanglongbing-infected citrus trees. Comput Electron Agric. 2013;96:103-10. doi:10.1016/j.compag.2012.12.002.
45. Gebbers R, Adamchuk V. Precision agriculture and food security. Science. 2010;327(5967):828-31. doi:10.1126/science.1183899.
46. Giller KE, Delaune T, Silva JV, Descheemaeker K, Van De Ven G, Schut AG, et al. The future of farming: Who will produce our food? Food Sec. 2021;13(5):1073-99. doi:10.1007/s12571-021-01184-6.
47. Gutierrez S, Tardaguila J, Fernandez-Novales J, Diago MP. On-the-go hyperspectral imaging for the in-field estimation of grape berry soluble solids and anthocyanin concentration. Aust J Grape Wine Res. 2018;25(1):127-33. doi:10.1111/ajgw.12376.
48. Guyer D, Miles G, Schreiber M, Mitchell O, Vanderbilt V. Machine vision and image processing for plant identification. Trans ASAE. 1986;29:1500-6. doi:10.13031/2013.30344.
49. Hadas E, Jozkow G, Walicka A, Borkowski A. Apple orchard inventory with a LiDAR-equipped unmanned aerial system. Int J Appl Earth Obs Geoinf. 2019;79:101911. doi:10.1016/j.jag.2019.101911.
50. Hafeez A, Husain MA, Singh SP, Chauhan A, Khan MT, Kumar N, Chauhan A, Soni SK. Implementation of drone technology for farm monitoring and pesticide spraying: A review. Inf Process Agric. 2022;9(2):123-34. doi:10.1016/j.inpa.2022.02.002.
51. Hahn F, Espinoza J, Zacarías U. Mango leaf monitoring with inductive and capacitive sensors and its comparison with trunk dendrometer measurements. Eng Proc. 2021;9(1):28. doi:10.3390/engproc2021009028.
52. Handique BK, Khan AQ, Goswami C, Prashnani M, Gupta C, Raju PLN. Crop discrimination using multispectral sensor onboard unmanned aerial vehicle. Proc Natl Acad Sci India Sect A Phys Sci. 2017;87(4):713-9. doi:10.1007/s40010-017-0443-9.
53. Hao F, Zhang X, Ouyang W, et al. Vegetation NDVI linked to temperature and precipitation in the upper catchments of the Yellow River. Environ Model Assess. 2012;17:389-98. doi:10.1007/s10666-011-9297-8.
54. Hassanalian M, Abdelkefi A. Classifications, applications, and design challenges of drones: A review. Prog Aerosp Sci. 2017
55. Helm C. Precision farming in South Africa. FarmTech 2006 Proceedings. 2005; 76-80.
56. Helm JM, Swiergosz AM, Haeberle HS, et al. Machine learning and artificial intelligence: Definitions, applications, and future directions. Curr Rev Musculoskelet Med. 2020;13(1):69-76. doi:10.1007/s12178-020-09600-8
57. Hunt ER, Hively WD, Fujikawa SJ, Linden DS, Daughtry CS, McCarty GW. Acquisition of NIR-green-blue digital photographs from unmanned aircraft for crop monitoring. Remote Sensing. 2013;5(2):1095-1110. doi:10.3390/rs2010290
58. Ishimwe R, Abutaleb K, Ahmed F. Applications of thermal imaging in agriculture: A review. Adv Remote Sensing. 2014;3(3):128-140. doi:10.4236/ars.2014.33011
59. Jensen JR. Remote sensing of the environment: An Earth resource perspective. 2nd ed. PrenticeHall, NJ; 2000.
60. Johnson L, Lobitz B, Armstrong R, Baldy R, Weber E, DeBenedictis J, Bosch D. Airborne imaging aids vineyard canopy evaluation. Calif Agr. 1996;50:14-18.
61. Joiner IA. Is it a bird, is it a plane, in Emerging Library Technologies. 2018;45-68.
62. Karlen DL, Sadler EJ, Busscher WJ. Crop yield variation associated with Coastal Plain soil map units. Soil Sci Soc Am J. 1990;54(3):859-865. doi:10.2136/sssaj1990.03615995005400030041x
63. Kavdir I, Guyer DE. Apple grading using fuzzy logic. Turk J Agric For. 2003;27(6):375-382.
64. Keskin M, Sekerli YE, Say SM, Topcueri M. Farmers' satisfaction level with GNSS-based tractor auto guidance systems in Adana province of Turkey. In: 13th Int Congress on Mechanization and Energy in Agriculture & Int. Workshop on Precision Agriculture; 2017 Sept 13-15;
65. King BA, Stark JC, McCann IR, Westermann DT. Spatially varied nitrogen application through a center pivot irrigation system. In: Robert PC, Rust RH, Larson WE, editors. Proc 3rd Int Conf Prec Agric. Madison, WI: ASA-CSSA-SSSA; 1996. p. 85-94. doi:10.2134/1996.precisionagproc3.c9
66. Kitamura S, Oka K, Takeda F. Development of picking robot in greenhouse horticulture. In: SICE Annual Conference; 2005 Aug 8-10; Okayama, Japan.
67. Kumar S, Moore KB. The evolution of global positioning system (GPS) technology. J Sci Educ Technol. 2002;11(1):59-80. doi:10.1023/A:1013999415003
68. St. Joseph, MI: Am Soc Agric Eng; 1988.
69. Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D. Machine learning in agriculture: A review. Sensors. 2018;18(8):2674. doi:10.3390/s18082674
70. Lodeman EG. The spraying of plants. New York, NY: The MacMillan Co.; 1916.
71. Lomte VM, Sabale S, Shirgaonkar R, Nagathan P, Pawar P. Fruit counting and maturity detection using image processing: A survey. Int J Res Eng Sci Manag. 2019;2(2):809-812.
72. Lowenberg-DeBoer J. The precision agriculture revolution is making the modern farmer. Foreign Affairs. May/June 2015 Issue.
73. Ma T, Xia Y, Inagaki T, Tsuchikawa S. Rapid and nondestructive evaluation of soluble solids content (SSC) and firmness in apple using Vis-NIR spatially resolved spectroscopy. Postharvest Biol Technol. 2021;173:111417. doi:10.1016/j.postharvbio.2020.111417
74. Maheswari P, Raja P, Apolo-Apolo OE, Perez Ruiz M. Intelligent fruit yield estimation for orchards using deep learning-based semantic segmentation techniques-a review. Front Plant Sci. 2021;12:684328. doi:10.3389/fpls.2021.684328
75. Maja JM, Ehsani R. Development of a yield monitoring system for citrus mechanical harvesting machines. Precision Agric. 2010;11(4):475-487. doi:10.1007/s11119-009-91411
76. Manaware D. Artificial intelligence: A new way to improve Indian agriculture. Int J Curr Microbiol Appl Sci. 2020;9(3):1095-1102.
77. Matese A, Di Gennaro SF, Santesteban LG. Methods to compare the spatial variability of UAV-based spectral and geometric information with ground autocorrelated data: A case study for precision viticulture. Comput Electron Agric. 2019;162:931-940. doi:10.1016/j.compag.2019.05.038
78. McBratney AB, Whelan BM. The null hypothesis of precision agriculture. In: Stafford JV, editor. 2nd European Conference on Precision Agriculture. Sheffield, UK: Sheffield Academic Press; 1999. p. 947-956.
79. McCann IR, Stark JC. Method and apparatus for variable application of irrigation water and chemicals. US Patent 5,246,164. Issued Sept 21, 1993.
80. Mesas-Carrascosa FJ, Perez-Porras F, de Larriva JEM, Frau CM, Aguera-Vega F, CarvajalRamirez F, et al. Drift correction of lightweight microbolometer thermal sensors on-board unmanned aerial vehicles. Remote Sensing. 2018;10(4):615. doi:10.3390/rs10040615
81. Mishra S, Mishra D, Santra GH. Applications of machine learning techniques in agricultural crop production: A review paper. Indian J Sci Technol. 2016;9(38):1-14. doi:10.17485/ijst/2016/v9i38/95032
82. Mohanty SP, Hughes DP, Salathe M. Utilizing deep learning for image-based plant disease detection. Front Plant Sci. 2016;7:1419. doi:10.3389/fpls.2016.01419
83. Mondal P, Basu M. Adoption of precision agriculture technologies in India and in some developing countries: Scope, present status and strategies. Prog Nat Sci. 2009;19(5):659-666. doi:10.1016/j.pnsc.2008.07.020
84. Monteiro A, Santos S, Gonçalves P. Precision agriculture for crop and livestock farming-Brief review. Animals. 2021;11(8):2345. doi:10.3390/ani11082345
85. Morimoto T, Suzuki J, Hashimoto Y. Optimization of a fuzzy controller for fruit storage using neural networks and genetic algorithms. Eng Appl Artif Intell. 1997;10(5):453461. doi:10.1016/S0952-1976(97)00047-X
86. Mulla DJ. Using geostatistics and spectral analysis to study spatial patterns in the topography of southeastern Washington State, USA. Earth Surf Process. 1988;13(5):389-405. doi:10.1002/esp.3290130505
87. Mustafa NBA, Ahmed SK, Ali Z, Yit WB, Abidin AAZ, Sharrif ZAM. Agricultural produce sorting and grading using support vector machines and fuzzy logic. In: 2009 IEEE international conference on signal and image processing applications. 2009. doi:10.1109/ICSIPA.2009.5478684.
88. Nagata M, Tallada JG, Kobayashi T. Bruise detection using NIR hyperspectral imaging for strawberry (Fragaria× ananassa Duch.). Environ Control Biol. 2006;44(2):133142. doi:https://doi.org/10.2525/ecb.44.133.
89. Naranjo PGV, Shojafar M, Mostafaei H, et al. P-SEP: A prolonged stable election routing algorithm for energylimited heterogeneous fog-supported wireless sensor networks. J Supercomput. 2017;73(2):733-755. doi:10.1007/s11227-016-1785-9.
90. Navalgund RR, Ray SS. Geomatics in natural resources management. In: Proceedings of Geomatics-2000. Pune; 2000 Jan 21-22. p. NR1-NR14.
91. Navalgund RR, Jayaraman V, Roy PS. Remote sensing applications: An overview. Curr Sci. 2007;93(12):17471766.
92. Navas E, Fernandez R, Sepulveda D, Armada M, Gonzalezde-Santos P. Soft grippers for automatic crop harvesting: A review. Sensors. 2021;21(8):1-27. doi:10.3390/s21082689.
93. Nielsen DR, Biggar JW, Erh KT. Spatial variability of fieldmeasured soil-water properties. Hilgardia. 1973;42:215259.
94. Oerke EC, Dehne HW, Schoenbeck F, Weber A. Crop production and crop protection: Estimated losses in major food and cash crops. Amsterdam: Elsevier Science; 1994.
95. Omary M, Camp CR, Sadler EJ. Centre pivot irrigation system modification to provide variable water application depths. Appl Eng Agric. 1997;13(2):235-239.
96. Palaniappan S, Nisha SP, Kumar MM, Sreehari K, Swasthik VK. Prediction of soil properties using image processing with ANN (artificial neural network) for crop cultivation. Indian J Nat Sci. 2019;9(53):17299-17308.
97. Palmer RJ. Progress report of a local positioning system. In: Kranzler G, editor. Automated agriculture for the 21st century. St. Joseph, MI: American Society of Agricultural Engineers; 1991. p. 403-408.
98. Panigrahy S, Ray SS. Remote sensing. In: Chadha KL, Swaminathan MS, editors. Environment and agriculture. New Delhi: Malhotra Publishing House; 2006. p. 361-375.
99. Parihar JS, Manjunath KR. Agricultural applications: Evolution during last 25 years. NNRMS Bull. 2013;58-75.
100. Patel PN, Patel MA, Faldu RM, Dave YR. Quadcopter for agricultural surveillance. Adv Electr Electron Eng. 2013;3:427-432.
101. Patil SS, Thorat SA. Early detection of grape diseases using machine learning and IoT. In: 2016 second international conference on Cognitive Computing and Information Processing (CCIP). 2016:1-5. IEEE. doi:10.1109/CCIP.2016.7802887.
102. Peterson DL, Hogmire HW. Tunnel sprayer for dwarf fruit trees. Trans ASAE. 1994;37:709-715.
103. Potts SF. Particle size of insecticides and its relation to application, distribution, and deposit. J Econ Entomol. 1946;39:716-720.
104. Priya R, Ramesh D. ML-based sustainable precision agriculture: A future generation perspective. Sustainable Comput Informat Syst. 2020;28:100439. doi:10.1016/j.suscom.2020.100439.
105. Priya R, Ramesh D, Khosla E. Crop prediction on the region belts of India: A Naïve Bayes MapReduce precision agricultural model. In: 2018 international conference on advances in computing, communications and informatics (ICACCI). 2018:99-104. IEEE. doi:10.1109/ICACCI.2018.8554948.
106. Qiu W, Dong L, Wang F, Yan H. Design of intelligent greenhouse environment monitoring system based on ZigBee and embedded technology. In: 2014 IEEE International Conference on Consumer Electronics (ICCEChina). 2014:1-5. doi:10.1109/ICCE-China.2014.7029857.
107. Megalingam RK, Sree GS, Reddy GM, Sri Krishna IR, Suriya LU. Food spoilage detection using convolutional neural networks and K Means clustering. In: 2019 3rd International Conference on Recent Developments in Control, Automation & Power Engineering (RDCAPE). Noida, India; 2019. p. 488-493. doi:10.1109/RDCAPE47089.2019.8979114.
108. Randall JM. The relationships between air volume and pressure on spray distribution in fruit trees. J Agric Eng Res. 1971;16:1-31. doi:https://doi.org/10.1016/S00218634(71)80002-1.
109. Rankin W. The geography of radionavigation and the politics of intangible artifacts. Technol Cult. 2014;55(3):622-674. doi:https://dx.doi.org/10.1353/tech.2014.0077.
110. Ray SS. Remote sensing for agricultural applications. GeoSmart India. Geomatics for Digital India, 2016 Mar 2; p. 1-8.
111. Ray SS, Neetu SM, Gupta S. Use of remote sensing in crop forecasting and assessment of impact of natural disasters: Operational approaches in India. Crop monitoring for improved food security. 2014.
112. Robertson MJ, Llewellyn RS, Mandel R, Lawes R, Bramley RGV, Swift L, Metz N, O'Callaghan C. Adoption of variable rate fertiliser application in the Australian grains industry: Status, issues and prospects. Precision Agric. 2012;13:181-199. doi:10.1007/s11119-011-9236-3.
113. Robinson C, Mort N. A neural network system for the protection of citrus crops from frost damage. Comput Electron Agric. 1997;16(3):177-187. doi:https://doi.org/10.1016/S0168-1699(96)00037-3.
114. Delalieux S, Zarco-Tejada PJ, Tits L, Bello MAJ, Intrigliolo DS, Somers B. Unmixing-based fusion of hyperspatial and hyperspectral airborne imagery for early detection of vegetation stress. IEEE J Sel Top Appl Earth Obs Remote Sens. 2014;7(6):2571-2582. doi:10.1109/JSTARS.2014.2330352.
115. Sahni V, Srivastava S, Khan R. Modeling techniques to improve the quality of food using artificial intelligence. J Food Qual. 2021;1-10. doi:10.1155/2021/2140010.
116. Saini DR, Prakash P, Kumar S, et al. Growing smarter: The role of artificial intelligence in agriculture. Biotica Res Today. 2024;6(8):406-409.
117. Saldana Ochoa K, Guo Z. A framework for the management of agricultural resources with automated aerial imagery detection. Comput Electron Agric. 2019;162:53-69. doi:10.1016/j.compag.2019.03.028.
118. Samuel AL. Some studies in machine learning using the game of checkers. IBM J Res Dev. 1959;3(3):210-9. doi:10.1147/rd.33.0210.
119. Sanaeifar A, Mohtasebi SS, Ghasemi-Varnamkhasti M, Siadat M. Application of an electronic nose system coupled with an artificial neural network for classification of banana samples during shelf-life process. In: 2014 International Conference on Control, Decision and Information Technologies (CoDIT); 2014 Apr 15-17; Paris, France. p. 753-7. doi:10.1109/CoDIT.2014.6996991.
120. Santesteban LG, di Gennaro SF, Herrero-Langreo A, Miranda C, Royo JB, Matese A. High-resolution UAVbased thermal imaging to estimate the instantaneous and seasonal variability of plant water status within a vineyard. Agric Water Manag. 2016;183:49-59. doi:10.1016/j.agwat.2016.08.026.
121. Schimmelpfennig D, Ebel R. On the doorstep of the information age: recent adoption of precision agriculture. Econ Inf Bull. 2011;80:1-31. doi:10.22004/ag.econ.291945.
122. Schueller JK, Bae YH. Spatially attributed automatic combined data acquisition. Comput Electron Agr. 1987;2(2):119-27. doi:10.1016/0168-1699(87)90022-6.
123. Schumann AW. Using precision agriculture technology for precise placement and variable rate fertilizer application. In: Nutrient BMPs: keeping water and nutrients in the root zone of Florida's horticultural crops. Apopka, FL: UF/IFAS; 2008. p. 13.
124. Shahrooz M, Talaeizadeh A, Alasty A. Agricultural spraying drones: advantages and disadvantages. In: 2020 Virtual Symposium in Plant Omics Sciences (OMICAS);
125. Silva CB, Moraes MAF, Molin JP. Adoption and use of precision agriculture technologies in the sugarcane industry of Sao Paulo state, Brazil. Precision Agric. 2011;12(1):6781. doi:10.1007/s11119-009-9155-8.
126. Sinha R, Kumar P, Singh PK, Tripathi N. Application of drones in precision agriculture: A review. J Agric Eng. 2020;57(2):33-46.
127. Smart RE, Dick JK, Gravett IM, Fisher BM. Canopy management to improve grape yield and wine quality: principles and practices. S Afr J Enol Vitic. 1990;11(1):317. doi:10.21548/11-1-2232.
128. Srbinovska M, Gavrovski C, Dimcev V, Krkoleva A, Borozan V. Environmental parameters monitoring in precision agriculture using wireless sensor networks. J Clean Prod. 2014;88:297-307. doi:10.1016/j.jclepro.2014.04.036.
129. Stafford JV, Miller PCH. Spatially selective application of herbicide to cereal crops. Comput Electron Agr. 1993;9(3):217-29. doi:10.1016/0168-1699(93)90040-8.
130. Stefas N, Bayram H, Isler V. Vision-based monitoring of orchards with UAVs. Comput Electron Agr. 2019;162:1-10. doi:10.1016/j.compag.2019.05.023.
131. Thompson JF, Stafford JV, Miller PCH. Selective application of herbicides to UK cereal crops. Paper presented at: American Society of Agricultural Engineers Annual International Meeting; 1990 Jul 24-27; Manhattan, Kansas, USA.
132. Torres-Sanchez J, de Castro AI, Pena JM, Jimenez-Brenes FM, Arquero O, Lovera M, et al. Mapping the 3D structure of almond trees using UAV-acquired photogrammetric point clouds and object-based image analysis. Biosyst Eng. 2018;176:172-84. doi:10.1016/j.biosystemseng.2018.10.018.
133. Travis JW, Skroch WA, Sutton TB. Effects of travel speed, application volume, and nozzle arrangement on deposition of pesticides in apple trees. Plant Dis. 1987;71(7):606-12.
134. Tu Y-H, Phinn S, Johansen K, Robson A. Assessing radiometric correction approaches for multispectral UAS imagery for horticultural applications. Remote Sens. 2018;10(11):1684. doi:10.3390/rs10111684.
135. Turing AM. Computing machinery and intelligence. In: Epstein R, Roberts G, Beber G, editors. Parsing the Turing Test. Dordrecht: Springer; 2009. p. 3-23. doi:10.1007/9781-4020-6710-5_3.
136. Tyler DA. Positioning technology (GPS). In: Robert PC, Rust RH, Larsen WE, editors. Proceedings of Soil Specific Crop Management. Madison, WI: American Society of Agronomy; 1993. p. 159-66.
137. Usha K, Singh B. Potential applications of remote sensing in horticulture: a review. Scientia Hortic. 2013;153:71-83. doi:10.1016/j.scienta.2013.01.008.
138. Valente J, Almeida R, Kooistra L. A comprehensive study of the potential application of flying ethylene-sensitive sensors for ripeness detection in apple orchards. Sensors (Basel). 2019;19(2):150. doi:10.3390/s19020372.
139. van der Wal T, Abma B, Viguria A, Prévinaire E, ZarcoTejada PJ, Serruys P, et al. Field copter: unmanned aerial systems for crop monitoring services. In: Precision agriculture '13; 2013 Jul 8-10; Wageningen, Netherlands. Wageningen: Wageningen Academic Publishers; 2013. p. 169-75. doi:10.3920/9789086867783_021.
140. Vanbrabant Y, Tits L, Delalieux S, Pauly K, Verjans W, Somers B. Multitemporal chlorophyll mapping in pome fruit orchards from remotely piloted aircraft systems. Remote Sens. 2019;11(12):1468. doi:10.3390/rs11121468.
141. Varshitha DN, Choudhary S. An AI solution for soil fertility and crop friendliness detection and monitoring. Int J Eng Adv Technol. 2021;10(3):172-5.
142. Verma L. China pursues precision agriculture on a grand scale. Resour Mag. 2015 Jul-Aug;22:18-9.
143. Walklate PJ, Richardson GM, Cross JV, Murray RA. Relationship between orchard tree crop structure and performance characteristics of an axial fan sprayer. Asp Appl Biol. 2000;57:285-92.
144. Wang N, Zhang N, Wang M. Wireless sensors in agriculture and food industry-recent development and future perspective. Comput Electron Agric. 2006;50(1):1-14. doi:10.1016/j.compag.2005.09.003.
145. Wang X, Yang K, Liu T. The implementation of a practical agricultural big data system. In: 2019 IEEE 5th International Conference on Computer and Communications (ICCC); 2019 Dec 18-21; Chengdu, China. p. 1955-9. doi:10.1109/ICCC47050.2019.9064475.
146. Webster R, Burgess TM. Sampling and bulking strategies for estimating soil properties in small regions. J Soil Sci. 1984;35(1):127-40. doi:10.1111/j.13652389.1984.tb00267.x.
147. Weinzierl R. Insect management updates for apples. Urbana-Champaign, IL: University of Illinois; 2015.
148. Wiles LJ, Wilkerson GG, Gold HJ, Coble HD. Modelling weed distribution for improved postemergence control decisions. Weed Sci. 1992;40(4):546-53. doi:10.1017/S0043174500058112.
149. Wu J, Yang G, Yang H, Zhu Y, Li Z, Lei L, Zhao C. Extracting apple tree crown information from remote imagery using deep learning. Comput Electron Agric. 2020;174:105504. doi:10.1016/j.compag.2020.105504.
150. Xiong Y, Ge Y, Grimstad L, From PJ. An autonomous strawberry harvesting robot: design, development, integration, and field evaluation. J Field Robotics. 2019;37(2):202-24. doi:10.1002/rob.21889.
151. Chen Y, Li Y. Intelligent autonomous pollination for future farming: a micro air vehicle conceptual framework with artificial intelligence and human-in-the-loop. IEEE Access. 2019;7:119706-17. doi:10.1109/ACCESS.2019.2937171.
152. Yadav N, Sidana N. Precision agriculture technologies: analyzing the use of advanced technologies, such as drones, sensors, and GPS, in precision agriculture for optimizing resource management, crop monitoring, and yield prediction. J Adv Zool. 2023;44:1-10.
153. Yossy EH, Pranata J, Wijaya T, Hermawan H, Budiharto W. Mango fruit sortation system using neural network and computer vision. Procedia Comput Sci. 2017;116:596-603. doi:10.1016/j.procs.2017.10.013.
154. Yu K, Sharp I, Guo YJ. Ground-based wireless positioning. Hoboken, NJ: John Wiley & Sons; 2009.
155. Zhang C, Kovacs JM. The application of small unmanned aerial systems for precision agriculture. Precision Agric. 2012;13(6):693-712. doi:10.1007/s11119-012-9274-5.