A Review of Drone Technology and Operation Processes in Agricultural Crop Spraying

Abstract

Precision agriculture is revolutionizing the management and production of agricultural crops. The development of new technologies in agriculture, such as unmanned aerial vehicles (UAVs), has proven to be an efficient option for spraying various compounds on crops. UAVs significantly contribute to enhancing precision agriculture. This review aims to determine whether integrating advanced precision technologies into drones for crop spraying enhances spraying accuracy compared to drones utilizing standard spraying technologies. To achieve this, 100 articles published between 2019 and 2024 were selected and analyzed. The information was summarized into five main areas: (1) improved spraying with agricultural drone technologies, (2) operational parameters, (3) spraying applications of chemical and natural compounds with agricultural drones, (4) evaluations of control pest efficacy, and (5) considerable limitations. Finally, considerations are presented on the advantages of drone technology with artificial intelligence (AI); the practical effects of reducing pesticides, which, in some cases, have reached a reduction of 30% compared to the recommended dose; and future directions for improving precision agriculture. The use of drones in precision agriculture presents technical and scientific challenges for the maximization of spraying efficiency and the minimization of agrochemical use.

1. Introduction

The Food and Agriculture Organization (FAO) projects that in the next 40 years, food production will need to increase by 70% to meet the growing demand for food driven by improved economic prosperity and population expansion. The main challenge for global agriculture is to feed an expanding population, which currently stands at seven billion people and is expected to reach around nine billion by 2050 [1].

Currently, agriculture is on the threshold of a new era, incorporating emerging technologies that enable innovative, more sustainable, and efficient production methods to meet the demands of a constantly expanding world. One such technology is the use of drones for spraying agrochemicals in agricultural fields, which has proven to be an effective alternative to manual spraying [2]. Additionally, the adoption of agricultural drones has safeguarded farmers’ health by reducing adverse health effects compared to manual pesticide spraying in crop fields [3].

This practice of using drones in crops, known as precision agriculture, has brought numerous advantages to farmers [4]. The most notable benefits include reduced agrochemical use, the early detection of pests and diseases, and timely, targeted interventions, which collectively minimize chemical use, waste, water, time, and money [5]. Moreover, the use of drones in the precise management of crop pests and diseases could be cost-effective and reduce the area where spraying pesticides is necessary [6].

However, as drones began to be used in crops, challenges related to the standardization of operational parameters (height, speed, nozzle type, angle and flow rate, spray width, etc.) [7] and application drift [8,9], as well as the type of agrochemical used [10], were identified. Therefore, the incorporation of advanced precision technology in drones used for crop spraying was adopted to improve efficiency in various areas [6].

Drones equipped with advanced spraying systems enable the precise application of agrochemicals, significantly reducing waste and preventing the contamination of non-target areas [11]. UAVs with RTK-GPS systems have demonstrated substantial herbicide savings and improved accuracy in pesticide application compared to traditional broadcast methods [12]. Additionally, sensors play a crucial role in precision agriculture by providing real-time data on soil and plant conditions, allowing farmers to make informed decisions [13]. The integration of multiple sensors and technologies, along with GIS, enhances the accuracy and comprehensiveness of data, further optimizing precision agriculture practices.

Initially, the implementation of computer vision technology in drones was primarily used to solve different problems related to capturing high-resolution images, multispectral data, pattern recognition, machine vision, object detection, and categorization, among other similar difficulties. This technology provides farmers with valuable information about crop health, soil conditions, and irrigation needs [14].

Recently, it has been observed that integrating conventional approaches with optimization methods improves accuracy and reduces computational time. Technologies such as the Internet of Things (IoT), wireless sensor networks, big data analytics, cloud computing, robotics, machine learning, and artificial intelligence have transformed traditional agriculture into precision agriculture [15]. This incorporation of artificial intelligence (AI) has significantly enhanced these existing technologies. AI enables the analysis of large volumes of agricultural data, improving decision-making and optimizing resources. From crop yield prediction to the early detection of diseases in crops, AI is revolutionizing modern agriculture, making processes more efficient and sustainable [16].

Therefore, precision agriculture emerges as a potent solution for confronting the dual challenges of climate change and food security. The incorporation of drones for the spraying of agrochemicals in crops represents a crucial advancement in this field. Similarly, the utilization of entomopathogenic microorganisms in crops plays a substantial role in mitigating climate change. It does so by reducing greenhouse gas emissions, safeguarding biodiversity, and improving the sustainability and resilience of agricultural systems. Hence, continuous research and development are crucial to maximizing these benefits.

The aim of this review is to assess whether the implementation of advanced precision technologies in drones used for crop agrochemical spraying improves accuracy compared to drones using standard spraying technologies. To achieve this, the reported spraying results from recent years are analyzed and compared. This study aims to provide relevant information for decision making in agriculture and sustainable resource management.

2. Search Strategy for Information

A comprehensive review of the scientific literature was performed using stages of identification, selection, and determination of the eligibility of studies. The choice of this analysis of the literature was based on its methodical, replicable, and exhaustive approach. This method aims to minimize the risks of bias by conducting precise and meticulous bibliographic research, thus providing a transparent and rigorous process from a scientific point of view. In addition, it offers a detailed description of the procedures followed by the researchers. In this study, the focus was specifically on analyzing the impact of crop spraying with agricultural drones. This review aims to provide a comprehensive and updated view of the most recent research in this emerging field.

2.1. Selection and Compilation of Studies

The step-by-step framework proposed by Parahoo [17] was used, which covers five distinct stages, as outlined in

Table 1. Steps associated with planning data collection for this study.

Phases	Description
1	Definition of the theme and guiding question of the study (PICO)
2	Definition of selection criteria (inclusion and exclusion of articles)
3	Selection of databases and descriptors for accessing the literature
4	Data collection
5	Analysis of results

Source: Adapted from Parahoo [17].

.

To formulate the research question for this study, the PICO strategy developed by Araújo [18] was adapted. This approach uses an acronym to represent the Problem (P), Intervention (I), Comparison (C), and Outcome (O). In this context, “P” refers to drones used for agricultural crop spraying, “I” denotes the implementation of advanced precision technologies in drones, “C” refers to drones that employ standard technology, and “O” alludes to an improvement in spray precision in agrochemical use.

Consequently, the research question for this study was articulated as follows: “Does the incorporation of advanced precision technology in drones used specifically for agricultural crop spraying lead to an improvement in spraying accuracy compared to drones that employ standard spray technologies?”. In order to comprehensively address this question, a search of scientific articles was conducted in June 2024.

2.1.1. Identification

The review was conducted by searching for articles in the electronic databases of PubMed and Scopus. Several descriptors were selected for this research, including “drone”, “spray”, “pesticide”, and “crop”. To efficiently cover all these descriptors and minimize the inclusion of irrelevant results, the Boolean operators AND/OR were used, and a standardized search string was used in all databases: ((drone OR Unmanned Aerial Vehicle) AND “spray”).

The inclusion criteria for the studies were based on the following aspects: (1) the article was published between 2019 and 2024; (2) the article was a research article; (3) the article included applications of crop spraying with agricultural drones; and (4) the article was written in English. Articles with relevant titles and abstracts related to the study topic were included. On the other hand, the following exclusion criteria were considered: (1) is not focused on applications of crop spraying with agricultural drones; (2) is a conference review; (3) is a letter, erratum, data article, or note; and (4) is written in a language other than English. In total, 136 articles were identified from PubMed, and 582 articles were found in Scopus. The search results were saved in the respective databases for later analysis. The process followed is shown in Figure 1.

2.1.2. Screening

The authors reviewed the titles of 281 identified articles. The criteria for advancing to the next stage included the following: (1) addressed applications of spraying, agrochemicals, entomopathogenic microorganisms, or plant extracts in crops; (2) detailed the preparation of pesticides for application with agricultural drones; (3) included the addition of adjuvants in pesticide preparations for application with agricultural drones; and (4) explored improvements in the operational parameters of drone flight to increase precision agriculture during spraying. Of the 281 initially selected articles, only 200 met these criteria. These articles were exported to the personal EndNote library for further analysis.

2.1.3. Eligibility

The authors examined the abstracts of the 200 selected articles. Articles that presented the following characteristics were excluded: (1) the full article is not available, (2) does not involve the use of drones in crops, and (3) does not refer to precision agriculture applications. In this phase, 100 articles did not meet the criteria, while 100 articles were selected for full-text reading, serving as the basis for this review.

2.1.4. Data Analysis

The 100 studies that successfully passed the Identification, Selection, and Eligibility stages were exported to Excel. A data analysis was performed using software to consolidate the results of various studies on the topic of this review. The following data were extracted from each study: year, author, title, purpose of the study, results obtained, and specific parameters such as the type of crop, pest or disease, entomopathogenic microorganisms, and/or plant extracts used to combat the pest or disease, drone type, tank volume, number of nozzles, nozzle type, flow range, droplet size, spray width, flight speed, optimal height, and application rate (Supplementary Materials, Table S1). The data extracted during this phase were analyzed and evaluated. The data analysis revealed heterogeneity in the objectives achieved using drones, which are summarized in Section 3. Through the data analysis, significant trends were identified in this field of study.

3. Spray Drones for Agricultural Applications

To date, the incorporation of drones in agricultural crop spraying has been the subject of numerous scientific studies. The literature reports that this technology has significantly increased spraying efficiency, achieving improvements of up to 60 times [19]. Precision agriculture, therefore, has opened a vast field of research encompassing various factors that influence precise spraying. This review will address four main areas: (1) improved spraying with agricultural drone technologies, (2) operational parameters, (3) spraying applications of chemical and natural compounds with agricultural drones, (4) evaluations of control pest efficacy, and (5) considerable limitations.

3.1. Improved Spraying with Agricultural Drone Technologies

Several researchers have dedicated efforts to developing technologies for improving automatic precision in pesticide spraying using agricultural drones. This involves achieving more effective droplet deposition on the target and controlling pesticide drift. Some notable advancements are outlined in

Table 2. Technology used in spraying drones.

Technology	Methodology	Improvement	Ref
CFD (Computational Fluid Dynamics) Theoretical	A discretization mathematical method from Computational Fluid Dynamics (CFD) to solve fluid dynamics problems	Theoretical support about droplet drift and deposition	[20]
	Regression analysis used a simulation dataset to train support vector regression and neural network models	Deposition distribution	[21]
	Complemented with orthogonal experiments	Uniform spray	[22]
	Complemented with wind tunnel experiments	Spray distribution, on-target deposition, and reduced droplet drift	[23,24]
	Considering velocity distribution of the downwash airflow	Droplet penetration	[25,26]
Real-Time Integrated System with Image Processing	Design and development of a real-time integrated system that utilizes image-processing algorithms on a commercial off-the-shelf (COTS) UAV platform	Image processing in high resolution	[27]
Machine Learning for Spray Area Recognition	A mutual subspace method (MSM)	Recognize the spray and non-spray areas	[11,28]
Intelligent Vision Sensor Node	A neural network for achieving uniform spraying, adjusting the spray flow rate based on the predicted deposition amount	Rapid collection of droplets deposition	[29]
Wireless Sensor Network-Based Flight Path Adjustment	A system incorporating deep reinforcement learning, particle swarm optimization algorithms, and neural network-based models for predicting wind speed and direction	Reduction in droplet drift	[8]
Integration of Remote Weed Mapping (UAV-IS)	Integration of remote weed mapping at specific sites	Reduction in pesticide use	[30]
Deep Learning Algorithms on Raspberry Pi for Weed Detection	Deep learning algorithms implemented on Raspberry Pi to activate herbicide spraying based on weed detection	Rapid differentiation and adjustment of spraying	[31]
You Only Look Once (YOLO)	Ag-YOLO, including the Intel Neural Compute Stick 2 (NCS2), and object detection algorithms in the software part	Two times faster	[32]
	YOLOv3-Tiny complemented with NVIDIA Jetson TX2 for Pest Recognition	Determine pest positions in real time	[33]
	YOLOv3 model integrates the Beidou RTK positioning system and the Manifold computer, along with a data time axis alignment method based on the Robot Operating System (ROS)	Real-time acquisition of parameters	[34]
	YOLOv5 and Multitemporal Detection. RGB sensor for real-time detection and georeferencing.	Real-time detection and identification of plants	[35]
	YOLOv7, YOLOv8, and beyond. Artificial intelligence complemented with methods such as Histogram Equalization (HE), Gaussian, and wavelet transform (WT).	Detection and identification of trees and reduction in pesticide use	[36]
Artificial intelligence	Algorithms on different datasets	Forecast plant stress	[37]
VRS System for Precision Spraying	Latency compensation algorithm (LCA)	Precise pesticide spraying, with desired coverage and deposition density	[38]
Light Detection and Ranging (LiDar)	Short-range remote sensing technology utilizing Light Detection and Ranging (LiDar) point clouds	Droplet drift and deposition	[39]

.

These studies provide valuable information for enhancing spray application precision using UAVs in various agricultural crops.

3.2. Operational Parameters

The drone-based spraying operation for agrochemicals encompasses a series of steps designed to achieve both efficiency and precision; see Figure 2.

3.2.1. Performing Drone Spraying

Conducting drone spraying in the field requires a systematic approach. Regardless of the type of drone used, the following steps must be followed to execute the spraying. First, designate an area for the drone’s takeoff and landing, ensuring it is fully charged and calibrated [40]. Appropriate personal protective equipment (PPE) should be used [41]. Then, conduct a safety briefing for all personnel, establishing communication and emergency protocols [5]. It is necessary to consider environmental regulations and avoid spraying near bodies of water and sensitive areas [42]. Additionally, a thorough pre-flight check of the drone is important, including the control system and GPS signal [31]. During takeoff, it is recommended to follow the manufacturer’s instructions and keep the drone within the line of sight. Next, activate the spraying equipment according to the flight plan and monitor the process in real time, adjusting the route if necessary [43]. Finally, upon completing all sections of the field, deactivate the spraying equipment and safely land the drone [5].

3.2.2. Flight Path Planning

Planning the feeding route and the GPS route for drone spraying is essential to ensure the efficient and precise application of the spraying solution, especially in complex environments or areas inaccessible to traditional machinery [5]. The process begins with obtaining a detailed map of the area to be sprayed, using satellite images to identify the terrain, obstacles, and field boundaries. Subsequently, flight planning software is used to define efficient routes, considering factors such as wind direction and obstacles. Among the reported studies, Liu et al. proposed an improved Dubins curve algorithm to generate obstacle avoidance routes, regardless of their size, and used a genetic algorithm (GA) to find the shortest route among flyable paths [44]. Gao et al. suggested an algorithmic system for controlling spraying using swarms of autonomous UAVs, employing a multi-agent area coverage approach called Heat-Equation-Driven Area Coverage (HEDAC) [11]. Liu et al. developed a dynamic genetic algorithm with the iterative binary optimization of ant colonies (DGA-ACBIO) for route planning in multiple tea fields in mountainous areas, achieving more than a 50% reduction in the search time and plant protection cost [45]. Tian et al. proposed an improved algorithm for precise route planning for the protection of each fruit tree, called Multi-source Ant Colony Optimization (MS-ACO) [46]. Meanwhile, Huang et al. evaluated the Sequential Quadratic Programming (SQP) method to determine whether drones can perform assigned tasks and make efficient decisions for coverage route planning [43]. According to previous studies, it is important to plan the overlap between adjacent routes to ensure uniform coverage and establish buffer zones to avoid spraying outside the designated area. The altitude and speed of the drone should be adjusted to achieve optimal and safe coverage. Finally, an appropriate flight pattern is chosen, and the data are transferred to the drone, monitoring its progress in real time to ensure a successful operation.

3.2.3. Field Spraying

In

Table 3. Agricultural crops sprayed with drones: operational parameters.

Cultivation/Crop	Drone	Tank Volume (L)	No. of Nozzles	Type of Nozzles	Spray Rate (L/min)	Drop Size (µm)	Flight Height (m)	Flight Speed (m/s)	Spraying Pattern	Volume Rate (L/ha)	Ref.
Rice	Drone-Freedom Eagle 1s	10	4	Hydraulic, LU110-01	1.92–2.36	132.8	1.5	3.3	ULV	15	[47]
Olive and citrus	DJI s1000+commercial UAV model	5	4	Fat fan nozzles; HARDI F-110 FLATFAN nozzle	0.22	119	2	4	ULV	0.5	[48]
Apple	DJI Agras T20	20	8	Flat-fan nozzles, SX11001VS	0–3.6	98.5–137.9	3.5	1.5	Inter-row	85.7	[49]
Hazelnut	DJI Agras MG-1P	10	4	Flat fan nozzles, Teejet XR11001VS	0.379	238–341	1.5 and 2	12	ULV	10	[50]
Redgram	E610P six-rotor electric	10	4	Flat fan nozzles, 2020A-132 series	0–3.2	200–508	1.6	3	N	54	[51]
Peach	3WYD-4-22A	22	4	Flat-fan nozzles, Lu120-015	0.79, 1.58, and 2.37	301, 420.54 and 512.51	1, 3, 5, 10, 20, and 50	1–3	N	33	[52]
Areca catechu	Jifei P20	10	4	Centrifugal nozzle	0.2–0.8	205.89	11.09	1.5	LV	22.5	[53]
Citrus	P30	16	4	Centrifugal atomization nozzles	0.5–0.9	100	4	6	N	5	[54]
Chestnut	T20k	16	8	Flat-fan hydraulic nozzle, XR11001VS	3.8, 6.0	170–265	3	5.8	ULV	40	[55]
Soybean	DJI Agras MG1-P	10	4	Air-induction flat-fan, AirMix 11001		270.97	2	5.6	N	10	[56]
Rice	E610P six-rotor battery-operated UAV	10	4	Flat fan nozzles, 2020A-132 series	3.2	288	1.3	3.5	N	54.6	[57]
Pear	DJI T20 series plant protection UAV	20	8	Flat-fan nozzles, SX11001VS/SX110015VS	0–6	130–300	5.5	2.5	N	90	[58]
Wheat	Hs0615	15	2	Centrifugal energy nozzles	1	200	1.5	5	N	15	[59]
Apple	DJI Agras t30	30	16	Flat spray nozzles, Teejet XR 11002 VK	0.5	278	4.2	2.08	N	140	[60]
Grapevine	Six-rotor UAV sprayer, Bly-c-agri model	10	2	Nozzle holders with diaphragm	1.24	257.79	5	0.5	LV	253.27	[61]
Guava	Hexacopter UAV	10	4	ULV nozzles	0.85	269	6.2	3	ULV	17	[62]
Citrus	DJI T30	30	16	Flat-fan hydraulic nozzles, 11001VS	0.42	300	5	3	N	75	[63]
Rice	DJI Agras T10	10	4	Flat-fan nozzles XR11001VS	1.8	163	2	4	N	15	[64]

Spraying pattern: N: normal; LV: low volume; ULV: ultra low volume.

, the heterogeneity of the operational parameters of spraying drones in different agricultural crops is summarized.

3.2.4. Wind Speeds (m/s)

Wind speed is a crucial factor in the spraying of agrochemicals with drones in the field. In 2019, the response surface method was used to evaluate and optimize the operational parameters of the drone, improving the uniformity of spray deposition based on the working height, working speed, and spray pressure [65]. Spray drift is directly related to wind speeds under field conditions. As the wind speed increases, so does the amount of detected drift, causing agrochemical droplets to be carried away from the target, thereby increasing the risk of contamination in undesired areas [66]. Another important relationship to consider is the interaction between the wind speed, liquid pressure, and droplet size. As the liquid pressure increases, droplet diameters decrease, becoming even smaller than 100 µm [9,67]. Wind speed can also affect the uniformity of coverage [68]. In strong wind conditions, it is more challenging to achieve a homogeneous distribution of droplets over the crop [69]. Additionally, the drone’s flight height and speed must be adjusted to minimize the negative effects of wind. Flying at a lower height and an appropriate speed can significantly reduce drift [19]. Therefore, it is highly recommended to perform spraying under moderate- or low-wind conditions to ensure effective application, guaranteeing that the droplets reach the target more precisely and efficiently.

3.2.5. Spray Height for Drones (m)

The suggested spraying height when using a drone can vary depending on the type of crop being treated and the target location, such as an insect or fungus within the crop. It is important to consider an optimal height to achieve uniform distribution. So far, according to Table 3, several studies have reported a range of heights ranging from 1 m in rice crops [47,57,64], wheat [59], hazelnut [50], and redgram [51] up to 11 m in A. catechu fields [53] and peach orchards [52].

Effective airflow control in orchard spraying can be achieved by adjusting the distance between the nozzle and the target area [70]. Reducing this distance generally ensures adequate air volume and speed while also minimizing spray drift. The flight altitude, defined as the drones’ height relative to the crop, represents the shortest distance droplets must travel to reach the target surface. Variations in altitude can influence the roto’s wind field strength [71]. Specifically, higher altitudes result in weaker downwash airflow at the canopy top, making it easier for sprayed droplets to drift with the crosswind [72].

In a study conducted by Wang using a QuanFeng120 UASS in a pineapple field under various meteorological conditions, it was observed that when the operational altitude was below 2.5 m, the mean speed ranged from 1.14 to 2.82 m/s, and 90% of the spray drift distance remained within 10 m. However, at altitudes up to 3.5 m with natural wind speeds between 2.02 and 3.59 m/s, the 90% spray drift distance extended to 33.54–46.50 m. Multiple experimental studies have consistently concluded that to minimize droplet drift, the maximum flight altitude should not exceed 2.5 m [73].

3.2.6. Application Rate in Crop Canopies: Adjusting Volume for Efficiency (L/ha)

In studies conducted in Nanguo pear orchards, considering canopy size is recommended for adjusting the application rate volume [74]. In garden plants, droplet deposition was evaluated, and optimal canopy performance for small- and medium-sized plants was observed under the following conditions: flight altitude of 1.5 m, spray volume of 180 L/ha, and flight speed of 2 m/s. Reducing the flight altitude, increasing the spray volume, and decreasing the flight speed can enhance the droplet distribution within the canopy [75].

In almond cultivation, two spraying methods were compared: drone-based application and the use of a traditional air sprayer. The general residue levels of the insecticide chlorantraniliprole in whole unpeeled almonds across canopy strata were similar between UAVs applied at 46.8 L/ha and 93.5 L/ha and comparative treatments with air sprayers applied at 935 L/ha [76]. Another study performed the same comparison in wheat crops, using an insecticide to combat the Sunn pest (Eurygaster integriceps Puton, Heteroptera: Scutelleridae), a significant pest. The UAV sprayer outperformed in terms of field capacity, insecticide dosage (mL/ha), spray volume (L/ha), reduced drift, and operator exposure risk [59]. In mountainous apple orchards, flying along and above rows at an application rate of 63.5 L/ha or more was reported as optimal for small and sparse trees (SS) [49].

3.2.7. Effective Swath Width

Spray coverage with drone application refers to the extent of the area that a drone can treat with agrochemicals in a single flight. This coverage depends on several factors, including the drone’s payload capacity, the configuration and spray angle of the nozzles, the flight altitude, and the drone’s speed.

Spray coverage is a significant aspect for the efficiency and effectiveness of agrochemical application. Optimal coverage ensures that pesticides are uniformly distributed over the target area, which is essential for effective crop treatment; see Figure 3.

Moreover, spray coverage can be adjusted to cater to divers’ needs. For instance, a drone can be programmed to fly at varying altitudes or speeds to modify the spray coverage, depending on the type of crop or the pest being treated. This adaptability allows for a more tailored approach to crop treatment, enhancing the overall effectiveness of the pesticide application process.

Interestingly, Hewitt et al. developed advanced spray calculators, both terrestrial and aerial, with the aim of optimizing coverage and retention while minimizing losses due to drift, bounce, fragmentation, and runoff. This innovative model combines the Agricultural Dispersal (AGDISP) and L-Studio systems, integrating detailed databases on spray systems. It includes precise information on the droplet size and the physical properties of tank mixtures, among other critical data. Additionally, it uses sophisticated algorithms to predict spray behavior in foliage. This tool is capable of simulating approximately one thousand different agricultural scenarios, providing a comprehensive solution for spray management under various conditions [77].

3.2.8. Nozzles

In this section, various aspects of nozzles will be addressed, including their types and sizes, pressure management and spray angle, specific applications with drones, spray volumes, and nozzle outlet design.

The type of nozzle determines the diameter of the sprayed droplets [78]. According to ISO 25358, droplet size is classified into reference categories: extremely fine (XF, <60 µm), very fine (VF, 61–105 µm), fine (F, 106–235 µm), medium (M, 236–340 µm), coarse (C, 341–403 µm), very coarse (VC, 404–502 µm), extremely coarse (XC, 503–665 µm), and ultra coarse (UC, >665 µm) [79]. The emitted droplet size varies with the operational parameters of the drone. Fine sprays are generated when there is a high energy component, low extensional viscosity, or low surface tension and are preferred to maximize coverage of the target plant surface. Conversely, nozzles that produce coarse or very coarse spray are chosen to minimize spray drift [77]. It is important to consider that the droplet size from the centrifugal nozzle mounted directly below the rotor on a four-rotor UAV can change depending on the rotation speed. For example, a study reported that when the speed increased from 2000 rpm to 17,000 rpm, the droplet size category changed from coarse (XC) to fine (F) [9].

The finest sprays are typically produced by full and hollow-cone nozzles or wide-angle flat-fan nozzles, whereas the coarsest sprays are usually produced by air-induction flat-fan and narrow-angle nozzles. For broadcast spraying over entire fields, wide-angle flat-fan nozzles (e.g., 110°) are generally the best choice. For weeds of different sizes and orientations, twin orifice designs may be more effective. On the other hand, for spot or patch spraying, where a sensor detects the weed and the sprayer activates only to spray detected weeds, narrow-angle flat-fan nozzles (e.g., 10–30°) are more suitable for targeting individual plants [77].

Wide-angle nozzles are a valuable tool for reducing spray height and minimizing drift. The spray angle and spray width are directly related to spray pressure, so careful pressure management can optimize coverage and spray effectiveness.

Liquids that are more viscous than water tend to form narrower spray angles, while liquids with lower surface tensions than water create broader spray angles. In scenarios where uniform distribution is crucial, it is important to operate the spray tips within the appropriate pressure range.

In the case of young cherry tree spraying using a hexacopter drone, dual flat nozzles were observed to have greater liquid deposition compared to single flat nozzles [80]. Additionally, flat fan nozzles with air induction (AIN) in vineyards promoted the deposition and uniformity of spraying, significantly reducing drift compared to hollow cone nozzles (HCN) across all tested UAVs [81].

In mountain terrace pear orchards, the air-assisted IDK90015 nozzle exhibited higher deposition and penetration, and its large droplet size also reduced drift risk. Using air induction nozzles and surfactant-based adjuvants can further improve spray deposition [80]. Further, a nozzle angle of 30° increases deposition by 76–94% and 61.04% at flight speeds of 1.2 m/s and 3 m/s, respectively [82].

In rice crops, flat fan nozzles produced finer droplets with desirable coverage, while air induction nozzles created larger droplets with consistent coverage at different flight speeds. Drones, combined with suitable adjuvants and nozzle types, can be effective for pest control in rice fields [83].

A study evaluated spray volumes about deposition effectiveness. Fine nozzles (LU120-01) at low volumes (<9.0 L/ha) resulted in lower deposition efficiency, whereas coarse nozzles (LU120-02, -03) with higher volumes (>16.8 L/ha) achieved optimal control with systemic insecticide. Additionally, a spray volume of 28.1 L/ha was effective with contact insecticide and fungicide [84].

For pesticide application in soybean crops using the Agras MG1-P (DJI Technology Co., Ltd., Shenzhen, China), nozzle types such as COAP 9001 (KGF Co., Ltd., Vinhedo, Brazil) and AirMix 11001 (Agrotop Spray Technology, Obertraubling, Germany) achieved the best deposition performance [56]. Finally, the outlet design of flat fan nozzles interacts with the nozzle type, being suitable for anti-drift and air induction nozzles but not standard nozzles [85].

3.2.9. Spray Pressure (MPa)

Spray pressure is the force to transform a liquid into small droplets [86]. This pressure is crucial for the effectiveness of spraying, as it determines the droplet size and the rate at which the orifices wear out. The dynamics of spraying, including the droplet size, velocity, and air drift, largely depend on the choice of nozzle, application pressure, and flow rate [23]. Nozzles can operate at pressures ranging from 1 to 7. Generally, smaller orifice diameters and higher pressures produce finer sprays [77]. Hollow cone spray nozzles are widely used and feature a diffuser with an opening for the pressurized spray. This process generates a rotational velocity vector in the fluid, increasing the pressure drop in the narrow zone between the diffuser and the circular orifice disk, resulting in a spherical spray pattern with fewer droplets in the center [56]. The droplet size in flat fan spray is classified as fine under general spraying pressure. In the AI nozzle, the sprayed droplet diameter is enlarged via air induction. The AI nozzle is less affected by wind than other nozzles [87]. Another study reports that droplet spray was greater for the turbulence nozzle than for air induction nozzles. However, increasing the working pressure led to an increase in the droplet spray regardless of the nozzle type [88].

3.2.10. Droplet Penetration Rate

The droplet penetration rate in the application of agrochemicals with drones refers to the effectiveness with which the applied products penetrate the target area, such as a crop or a piece of land. A study reported that vortex formation during spraying significantly influences droplet deposition. Specifically, stronger vortices lead to increased droplet penetration within the canopy depth [89].

3.2.11. Droplet Deposition (µL/cm²)

In medium-density olive orchards, it was observed that crop depositions were significantly lower when a UAV sprayer was used [90]. On the other hand, a study provides comprehensive data to encourage innovation in the use of UAVs for crop protection programs in orchards with vertical trellis systems, such as FT orchards. This study introduced a new pear cultivation model called “standard flat espalier pear orchards with double primary branches” (FT orchard). Additionally, this work included a thorough analysis of canopy deposition methods and offered recommendations for UAV development and applications [58]. In the case of peanut crops, the results indicated a significant difference in droplet deposition between phytosanitary UAVs and electric backpack sprayers. It is recommended to use an application volume of 22.5 L/ha without adding vegetable oil adjuvants for field operations [91].

3.2.12. Drift

Drift is a phenomenon that occurs during the application of agrochemicals, where droplets containing active ingredients do not reach their intended target. This phenomenon is observed in small droplets, typically less than 200 microns in diameter, which are easily deflected by wing or other weather conditions, higher release heights, and conditions that favor evaporation, such as higher air temperatures and lower relative humidity [77]. Weicai et al. focused their research on the independent factors influencing the deposition characteristics of droplets sprayed by phytosanitary UAVs. Additionally, experimental methods and mathematical analysis models are explored to study both the deposition and drift of these droplets [92].

On the other hand, Dubuis et al. provide essential data on the potential drift of drone spraying, which is relevant for environmental and health risk assessments associated with these systems [60]. This information is crucial for understanding and mitigating the potential impacts of aerial spraying on the environment and human health.

3.2.13. Post-Spraying Operations

After completing drone spraying operations, it is crucial to perform several post-spraying tasks to ensure proper cleaning, maintenance, and data management. First, the drone’s battery should be removed and replaced if necessary, ensuring used batteries are stored and charged correctly [93]. Next, it should be carefully checked that all parts are securely closed to prevent leaks during transport until the equipment is cleaned. Once cleaning begins, the tank must be completely emptied [94] and then rinsed with clean water to remove any remaining traces of the spraying solution [93]. It is advisable to use a soft brush or nozzle-cleaning tools to clean the nozzles thoroughly. Depending on the type of spraying solution used, specific cleaning agents recommended by the manufacturer may be necessary to dissolve residues that water alone cannot remove [5]. It is important to ensure that all components are completely dry before reassembling or storing them to prevent mold, bacterial growth, and corrosion. The equipment should be stored in a safe, clean, dry, and well-ventilated area, away from direct sunlight [95].

Finally, it is highly recommended to keep a detailed log of the cleaning process, including the cleaning agents used, the date of cleaning, and any observations or issues encountered [96]. Post-spraying operations are critical for maintaining the longevity of the equipment, ensuring accurate data analysis [79], and making improvements for future operations [5].

3.2.14. Evaluation of Spraying Using Water-Sensitive Paper

Water-sensitive paper (WSP) is an essential tool for evaluating and improving drone spraying operations. This paper changes color upon contact with water, allowing for the analysis of spray patterns, droplet size, drift potential, coverage uniformity, adjuvant effects, comparative studies, and quantitative measurements [5].

In a rice crop, WSP was used as a sampler to collect droplets at different flight speeds and spray rates. After the statistical analysis of droplet deposition density, optimal operating conditions for spraying an organic liquid fertilizer were identified [97].

Several authors have used WSP to evaluate the operational parameters of sprayers with different nozzle types, collecting data on the droplet spectrum such as coverage, density, droplet size, and drift potential [61,86], and in Conilon coffee plants to evaluate the effect of centrifugal nozzle rotation and operational height on the efficacy of foliar fertilizer application [98].

By placing WSP in different locations within the spray area, valuable information about liquid distribution is obtained. In redgram crops, WSP was implemented in the upper, middle, and lower positions of the leaves to analyze the droplet size, deposition rate, droplet density, and area coverage, both in target and non-target areas, to increase precision in insecticide applications [51]. This tool evaluates spray drift [99], ensuring uniform coverage and making informed decisions to optimize application parameters.

In a guava orchard, the azadirachtin 0.15% EC biopesticide based on organic neem seeds was applied, and the coverage, droplet density, droplet size, and uniformity coefficient were evaluated using WSP [62]. Additionally, WSP was reported to be used as a collector to assess the effects of a typical tank mix adjuvant (Nong Jian Fei) concentration on the contact angle and droplet distribution in citrus tree canopies [63].

Another study compared the qualitative and quantitative results obtained using WSP and Medley Velvet (MV), a food dye tracer, and found that MV provides a more accurate analysis [100]. This multifaceted approach not only improves spraying efficiency but also promotes more sustainable and effective agricultural practices.

3.2.15. Tracers

In precision agriculture, assessing spray position is crucial to ensure efficient pesticide application. Various tracers have been used for this purpose. Gao’s study demonstrated that using Allura Red as a tracer is feasible and practical, without altering the physicochemical properties of pesticides [101]. Another study by Wang employed Rhodamine-B and WSP as tracers [84]. Additionally, Tartrazine has been used as a tracer [89], along with Brilliant Blue [56] and Brilliant Sulfoflavine (BSF17, lote 1F-561, Waldeck) at a concentration of 4 g/L for tests in Weingarten and Pyranin at 120% with a concentration of 5 g/L in Geisenheim [102]. These tracers allow for the precise evaluation of the pesticide dispersion and position during spraying.

Among the advantages of using tracers is that the results obtained are more precise and realistic, as they are applied across the entire evaluated area. This allows for uniform data collection during monitoring and evaluation, facilitating the tracking of agrochemical distribution and helping to identify areas that require more attention. As a result, productivity and crop quality can be improved by ensuring that crops receive the appropriate amount of nutrients and protection.

However, the disadvantages include the difficulty in obtaining tracers, the high costs for small farmers, the stains they can leave in the tank and on the crops, and the strict regulations that may limit their use.

3.3. Spray Applications of Chemical and Natural Compounds with Agricultural Drones

Several studies have reported the effectiveness of applying chemical compounds, including pesticides, insecticides, herbicides, and organic compounds such as biopesticides and entomopathogenic microorganisms, using UAVs for pest and disease control in crops. This approach is particularly valuable in inaccessible areas.

3.3.1. Chemical Compounds

The literature documents successful cases of applying various agrochemicals using unmanned aerial vehicles. These studies cover diverse environments, including forests, wheat fields, cotton, red grain, corn, and chestnut trees.

Drones have been evaluated for insecticide application in trees. The high efficacy observed in controlling the target pest indicates that UAV technology is well suited for insecticide application in forests [103].

In wheat crops affected by Fusarium head blight and mycotoxin contamination, nanoformulated prothioconazole (a systemic fungicide) at an 8% concentration yielded promising results. Compared to other spraying equipment, the DJI T16 UAV sprayer generated fewer prothioconazole residues, reducing the risk of human exposure to pesticides [2].

Ultra-low-volume (ULV) sprays of thidiazuron and diuron in cotton crops exhibited better wetting properties than commercially available suspension concentrates. Additionally, the volatilization rate was lower [104].

In red gram cultivation, the insecticide imidacloprid (a.i. 17.8SL) was sprayed, demonstrating that UAV usage enhanced the insecticide’s penetration into crop leaves. This led to increased droplet deposition, droplet density, area coverage, and penetration across all layers (upper, middle, and lower) of the plants [51].

In maize crops, granular formulations containing 0.25% chlorantraniliprole + 0.15% emamectin benzoate (or higher concentrations) were evaluated for the more effective and long-lasting control of fall armyworm during the whorl stage [105].

Multiple crops face threats from pests such as fall armyworms, grasshoppers, and aphids. The successful spraying of Metarhizium acridum using UAVs has been achieved to combat desert locusts [106].

In young chestnut crops, the efficacy of ultra-low-volume pesticide application via UAV surpassed conventional methods in pest control [106].

For cotton crops, the effect of treating with dinotefuran 8% + thiacloprid 48% WG at the recommended dose (625 g a.i./ha) and 25% less than the recommended dose (469 g a.i./ha) was demonstrated. The latter dose shower’s effectiveness suggests the possibility of reducing pesticide dosage when using UAVs without compromising pest reduction and yield levels [107].

In wheat crops, herbicide spraying using UAVs also proved effective, contributing to achieving Sustainable Development Goal (SDG) 2 for Zero Hunger by promoting plant protection and sustainable crop production [108].

3.3.2. Adjuvants in Drone-Based Pesticide Application

The use of adjuvants in drone-based pesticide applications significantly enhances the physical and chemical properties of formulations, optimizing coverage and penetration. Studies show that selecting the appropriate adjuvants and their concentrations is crucial for maximizing efficacy and minimizing risks.

Regarding the development of agrochemical formulations, adjuvants used in ultra-low-volume spraying can significantly enhance the physical and chemical properties of the formulation, optimizing its wetting and spreading capabilities. These benefits include improved surface tension, increased viscosity, and more appropriate droplet sizes. To maximize pesticide dosage administration, it is essential to select appropriate types and concentrations of adjuvants in the tank mix. However, it is important to note that adding inappropriate adjuvants can pose potential risks [109].

Several studies have reported better results when using adjuvants for drone-based spraying. For instance, in the case of cotton aphids (Aphis gossypii), a combination of the insecticides cycloxaprid, imidacloprid, and lambda-cyhalothrin with the adjuvant Silwet DRS-60 improved control [110].

Another study emphasized the importance of reducing spray volume for efficiency. They combined the recommended dose of the insecticide chlorantraniliprole (111 g a.i./ha) with the adjuvant mixture of methyl esters of C16-C18 fatty acids, polyalkyleneoxide modified polydimethylsiloxane, and alkylphenol ethoxylate (0.06% v/v). This combination enhanced coverage. The methylated seed oil (MSO) component reduced evaporation and improved tissue penetration, while the organosilicone component reduced surface tension and facilitated better droplet distribution [76].

Similarly, another study explored the addition of anionic and non-ionic adjuvants to selected solvents to create a stable pesticide loading system. They also included methyl oleate, a methyl vegetable oil adjuvant, to reduce volatility and enhance the deposition of small droplets. Methyl oleate is biodegradable and has low toxicity. Additionally, they found that adding 25% chlorinated paraffin to the formula increased viscosity and density, reducing drift and phytotoxicity risk [104].

In pepper cultivation, the adjuvant Puliwang demonstrated the best results for defoliant spraying, achieving higher defoliation rates and improved droplet deposition. Other adjuvants used in this crop include AS-910N, YS-20, and Manniu [111].

In peach orchards, imidacloprid exhibited the highest deposition efficiency. The deposition amount and normalized deposition within the canopy were greatest at a flight speed of 2 m/s, accompanied by minimal ground loss beneath the canopy [52].

For citrus tree crops, the tank mix adjuvant Nong Jian Fei (NJF) was used, evaluating the contact angle (CA) and droplet distribution within the citrus tree canopy [63].

In wheat crops, the tank mix adjuvant 8860 significantly impacted the physicochemical properties of spray dilutions. It not only reduced droplet bounce but also improved wetting and dispersion on wheat leaves, enhancing effective tebuconazole deposition. Even when reducing the dosage by one-third, the spray solution demonstrated excellent disease control and efficient active ingredient deposition on wheat leaves [112].

In rice cultivation, the methyl oxirane adjuvant with mono (3,5,5-trimethylhexyl) ether significantly reduced the dynamic surface tension of the spray dilution, inhibiting the bounce of large droplets and spray drift. This makes it promising for clorantraniliprole deposition [113]. Additionally, the glyceryl derivate and blend of alkoxylated polyether (94% w/v) adjuvant remained effective even with a 30% reduction in pesticide dosage [114]. Another finding in rice crops involved using Wonderful Rosin (adjuvant-1) and Tiandun (adjuvant-2) at a concentration of 0.5%, resulting in better control against rice grasshoppers [64]. Interestingly, emergency compound applications, such as pretilachlor, complemented weed control effectiveness in rice cultivation [115].

In peanut cultivation, MO501 significantly reduced the droplet size (Dv) to less than 100 µm, preventing bounce on leaves. Silwet 408 achieved complete wetting and superior spreading, becoming effective at a concentration of at least 0.2%, with bounce inhibition starting at 0.5%. Even at low concentrations, XL-70 demonstrated excellent regulation, suppressing impact while promoting spread. Oil dispersion (OD) in the formulation significantly reduced fine particle drift and prevented bounce at dilution ratios up to 250 times, improving dosage administration [109]. Finally, suspension concentrate (SC) formulations containing low doses (g/ha) of high-dispersibility organosilicone alkoxylate surfactants resulted in comparable foliar coverage to higher spray volumes [116].

3.3.3. Natural Compounds

Regarding the delivery of beneficial microorganisms, interesting studies such as that by Del Pozo et al. documented the effects of lacewing eggs of Chrysoperla rufilabris mixed with rice hulls and released by DJI Matrice 600 Pro drone (DJI Technology Co., Ltd., Shenzhen, China)at a rate of 74,131 eggs/ha on the densities of lettuce aphid Nasonovia ribisnigri (Mosley) (Hemiptera: Aphididae) in organic romaine lettuce fields. According to their findings, the drone flight uniformly distributed the released material within each treated area, resulting in a decrease in aphid density (15.6–150.0 aphids/lettuce head) compared to untreated plots (32.1–257.9 aphids/lettuce head). They also documented the quality of each lacewing shipment, recording egg hatching rates under controlled conditions. After four shipments, the hatching rates averaged 92.4%; therefore, the use of drones for these releases makes this strategy attractive and economically viable [117]. Other researchers developed an intelligent delivery system using an M45 electric multirotor UAV to release Trichogramma ostriniae (a natural enemy of pests) in corn fields autonomously. The UAV flew accurately, with minimal deviation from planned routes. It achieved a 99.33% effective coverage rate for releasing natural enemies. Post-delivery, field investigations indicated an average pest control of 83.70%, demonstrating its effectiveness [118]. In addition, researchers have developed a data-driven framework to predict the distribution patterns of vermiculite dispensed from a hovering UAV. This prediction considers the UAV´s movement state, wind conditions, and dispenser settings [119].

3.4. Evaluations of Pest Control Efficacy

Evaluating the efficacy of pest control in crops when applying agrochemicals with drones is crucial for several reasons. First, drones offer high precision and efficiency, targeting specific areas and reducing the amount of agrochemicals needed, which minimizes the environmental impact. Efficacy evaluations ensure that this precision translates into effective pest control. Second, by assessing the effectiveness of drone applications, researchers can optimize the use of agrochemicals, ensuring the right amount is used at the right time, leading to cost savings for farmers. Third, proper evaluations help in understanding the environmental footprint of using drones for agrochemical applications, including potential drift, runoff, and non-target effects, which are critical for sustainable agriculture practices.

Moreover, efficacy studies are often required to meet regulatory standards, providing the necessary data to demonstrate that drone applications are safe and effective and facilitating regulatory approvals and market adoption. Continuous efficacy evaluation can also identify areas for technological improvement, such as advancements in GPS accuracy, spray control software, and the development of better nozzles and flow meters. Additionally, these evaluations provide valuable data for making informed decisions about pest management strategies, helping to develop best practices and guidelines for the use of drones in agriculture. Finally, demonstrating the effectiveness of drone-applied agrochemicals builds confidence among farmers, encouraging them to adopt this technology, leading to the broader acceptance and integration of drones in agricultural practices. Overall, efficacy evaluations are essential for ensuring that using drones in applying agrochemicals is both effective and sustainable, benefiting farmers, the environment, and the agricultural industry.

Table 4. Effectiveness of managing agricultural crops pests using drones.

Crop	Drone	Application	Pest	Control Efficacy	Reference
Rice	Freedom Eagle 1s (Anyang Quanfeng Aviation Plant Protection Technology Co., Ltd. Anyang, China)	Treatment 1, 3, 5	Rice planthoppers	90.8%	[47]
Wheat	HS0615 (Kasbo Kar Jahan Jadid Co., Iran)	Deltamethrin	Sunn pest	96%	[59]
KALRO * Station	DJI Agras T20 (DJI, Shenzhen, China)	Metarhizium acridum	Desert locusts	80%	[106]
Sugarcane	3WWDZ-10A (XAIRCRAFT Technologies Co., Ltd., Guangzhou, China)	Abamectin and lufenuron	Stem borer	40%	[120]
Sugarcane	3WWDZ-10A (XAIRCRAFT Technologies Co., Ltd., Guangzhou, China)	Chlorfenapyr, chlorantraniliprole, and lufenuron.	Fall armyworm	94.94%	[121]
Pepper	DJI T16 (DJI Technology Co., Ltd., Shenzhen, China)	Cymoxanil_mancozeb and flutamide. One-third of the pesticide concentration compared to conventional spraying	Phytophthora capsica and aphids	94.34%	[122]

* KALRO: Kenya Agricultural and Livestock Research Organization Station.

summarizes the effectiveness of managing agricultural crops pests using drones.

3.5. Considerable Limitations

It cannot be overstated how important it is to conduct adequate replications in time and space for studies using agrochemicals with spraying drones.

Richarson et al. (2019) conducted a comprehensive study to evaluate the efficiency and precision of pesticide application using a UAV, replicating the experiment 65 times under various operational and meteorological conditions. The results revealed a highly variable swath pattern with significant unexplained variance. The study also highlighted the need for improvements in UAV hardware and software, such as more accurate GPS systems, flexible spray control software, and the incorporation of flow meters to track and record the actual amount of spray applied. Additionally, developing mechanistic models to better understand the complex interactions between operating variables and environmental conditions is essential for enhancing the precision and efficiency of UAV spray applications [123].

The lack of agreed-upon guidelines or testing protocols for standardizing the conduct of pesticide application with spray drones is a significant issue. This inconsistency often results in experimental aspects that limit the robustness or reliability of the product, making it less useful in a regulatory context. For instance, the diversity in data collection and reporting methodologies, as well as the absence of standardized protocols, complicates the comparison and validation of results across different studies. Additionally, the lack of adequate replications in the reported studies is a major constraint, impeding the ability to improve the technology effectively. This variability and lack of standardization hinder the development of a consensus on the performance and safety of UASS, which is crucial for regulatory approval and broader market adoption [79].

Fritz et al. (2020) reported that the small platform size of current UAVs intended for broadcast applications, combined with the limited number of nozzles, may lead to inconsistent deposition patterns over time, complicating the achievement of uniform broadcast deposition [124].

4. Conclusions

This study summarizes the evolution of advanced technologies in agricultural drones used for spraying various crops. Recent technological advancements have significantly transformed agrochemical spraying, presenting opportunities for further innovation. From drones and remote sensing to precision agriculture and artificial intelligence (AI), these technologies are redefining how crops are safeguarded. Precision agriculture involves the administration of optimal amounts of water, fertilizers, and pesticides based on real-time data from field sensors. Decision support systems guide actions such as irrigation and fertilization, while AI-equipped drones autonomously survey large areas and perform selective spraying.

Additionally, drones have proven to be useful tools for increasing spraying precision while simultaneously reducing water and chemical usage. This has allowed for desirable results, which, in some cases, have maintained their efficacy even with a 30% reduction in pesticide dosage.

Future directions for improving precision agriculture should focus on integrating advanced technology and/or artificial intelligence into agricultural drones. This would enable faster and more accurate data collection, leading to improved or even automated decision-making managing operational parameters, spray areas, and optimal dosage amounts for spraying, as well as the delivery of entomopathogenic microorganisms. Further, improving agrochemical formulations and evaluating the addition of adjuvants could enhance the efficiency of crop treatments. As this integration progresses, crop spraying with drones will become even more precise, efficient, and cost-effective.

However, each crop faces different pests and diseases, which determine the type of agrochemical or natural compound to use and the operational parameters configured in the drone. The heterogeneity limited this research to comparing operational parameters and agrochemical doses between crops to explore the optimal conditions. Therefore, much research remains to be conducted.

5. Future Directions

Crops have significantly benefited from drone spraying. Advanced GPS navigation systems, which enable real-time monitoring and precise spraying routes, along with sensors and advanced imaging technology such as thermal cameras and LiDar systems, have enhanced spraying precision. Current trends indicate that drones with advanced technologies and deep reinforcement learning algorithms could operate automatically with scheduled times and routes, adjusting operational parameters in real time to maximize spraying efficiency, minimize agrochemical use, and adapt their use to a wider variety of crops.

Additionally, it is important to consider the distribution of beneficial organisms in specific areas where they are needed for biological control, contributing to environmental care. Finally, the incorporation of artificial intelligence and the development of algorithms that regulate the volume and dosage of applications in specific areas, according to crop needs, could increase the effectiveness of biological control and reduce distribution costs.