Alaa Subr

Weed control with chemicals is a challenging process that should be performed in a rational way to reduce their negative impact on the surrounding environment. The growth of artificial intelligence algorithms encourages researchers to develop smart spraying robots that detect and spray weeds and distinguish them from the main crop which leads to sustainable use of these chemicals and achieves some of the sustainable development goals. However, few studies are available to comprehensively compare different versions of YOLO algorithm to detect weed. In this research, seven versions of YOLO algorithms were evaluated for their performance to detect and spray four types of weeds, namely, Cultivated licorice ( Glycyrrhiza glabra L.), Dyer’s Croton ( Chrozophora verbascifolia ), Lambsquarters ( Chenopodium album L.), and Puncturevine ( Tribulus terrestris L.) using a locally manufactured remotely controlled spraying robot. The results showed that YOLOv6n surpassed other algorithms which achieved the highest precision (0.89), recall (0.80), F1-score (0.84), mAp@0.50 (0.86), inference speed (18.83 fps), in addition to the field indicators including true positive rate (0.83), false negative rate (0.17), false positive rate (0.19), true negative rate (0.81).

Spraying pesticides is one of the most common procedures that is conducted to control pests. However, excessive use of these chemicals inversely affects the surrounding environments including the soil, plants, animals, and the operator itself. Therefore, researchers have been encouraged to develop robotic sprayers that can apply pesticides at variable rates as needed in the field. In this study, a remotely controlled sprayer with two modes (variable rate and constant rate applications) was developed and evaluated for some spray characteristics and application accuracy metrics when controlling weeds at two travel speeds. The variable rate mode resulted in a high precision, recall, and accuracy in detecting weed and applying herbicide that was 90%, 100%, and 94%, respectively. Moreover, the spray coverage, droplet density, and the deposition on weed using the variable rate mode were 34.16%, 127.64 deposites ∙ cm–2, and 7.67 μl ∙ cm–2, respectively. The result also revealed that the spray coverage, droplet density, and the deposition were less sensitive to the travel speed when adopting the variable rate mode compared to the constant rate mode.

The change in the size of the droplets during the pesticide application process could have a negative impact on the percentage of drift or the losses of pesticides to the environment. One of the factors that could affect the droplet size produced from a single nozzle is the internal design of the nozzle itself, in addition to the wear of the nozzle orifice as a result of the usage time. In this research, three types of nozzles with different internal designs were used (Turbo TeeJet (TT), Turbo TwinJet (TTj 6011003), and Drift Guard (DG 11003)). The nozzles were subjected to an accelerated wear test for one hundred hours, and different droplet size parameters (Dv 0.1, Dv 0.5, Dv 0.9), relative span (RS), and Sauter mean diameter (SMD) were measured during and after this test. The measurements were made using the Sympatec HELOS-VARIO/KR device in fifteen positions along the spray swath. The results of the study showed that the droplet size (Dv 0.5) generally increased for the DG 11003 and TTj 6011003 nozzles after the accelerated wear test (worn nozzles), while there was a decrease in Dv 0.5 for the TT 11003 nozzles. The DG 11003 nozzles (before and after the wear test) had the highest percentage of droplets with a size smaller than 150 μm (%< 150 μm) compared to the TT 11003 and TTj 6011003 nozzles. Moreover, the %< 150 μm was higher in the middle position of the spray swath for the three types of nozzles and the new and worn nozzles.

This study was aimed to reduce the amount of the sprayed solution lost during trees spraying. At the same time, the concentration of the sprayed solution on the target (tree or bush) must be ensured and to find the best combination of treatments. Two factors controls the spraying process: (i) spraying speed (1.2 km/h, 2.4 km/h, 3.6 km/h), and (ii) the type of sensor. The test results showed a significant loss reduction percentage. It reached (6.05%, 5.39% and 2.05%) at the speed (1.2 km/h, 2.4 km/h, 3.6 km/h), respectively. It was noticed that when the speed becomes higher the loss becomes less accordingly. The interaction between the 3.6 km/h speed and the type of Ultrasonic sensor led to a decrease in the percentage of the spray losses reached to 1.69. For the coverage percentage, the increase in the spraying speed from 1.2 km/h to 2.4 km/h, and then to 3.6 km/h led to a significant decrease in the percentage of coverage (from 17.73% to 13.14%, and then to 11.12%), respectively. The interaction between the type of sensor and the speed has significantly affected the spray density. The speed was 3.6 km/h, and the type of Ultrasonic sensor was superior in obtaining the highest spray density of 83.2 drops/cm2.

The research objective focuses on spraying the leaves of the plant from the top and bottom through a spraying machine designed and made of aluminum with a movable arm equipped with a nozzle holder divided into three parts and each piece contains a nozzle of the type (Flat Fan 120-C3) as the machine was tried in a greenhouse with a study of the effect of changing the positions of the upper and lower piece of the tube carrying the nozzles to four levels (A1, A2, A3, A4) and the effect of pressure change on two levels (2,4) bar and studying the effect of the previous factors on some of the characteristics of the study, Spray quality on adaxial of leaf, Spray quality on the abaxial surface of a leaf, spraying on all test sheets placed on the eggplant plant. The experimental design is RCBD according to the SPLIT-PLOT system and for three repeaters using the least significant difference (LSD) with a probability level of 0.05. The results showed that the A2 situation was significantly superior to all the studied qualities, and the pressure (4 bar) was significantly superior to all the studied qualities. As for the interaction position of boom (A4) with the pressure of (4bars), its result in all qualities was less than the rest of the coefficients, and it is not significant at the level of (0.05).

One of the goals of adding adjuvants to agricultural spray solutions is to enhance the droplet size characteristics of this spray. Droplet size, in turn, has an influence in the deposited spray quality, in addition to the drift and losses of spray to off-target places. The aim of this research was to evaluate the effect of adding adjuvants to two types of water from different sources on the droplet size characteristics. Two types of adjuvants were employed in the tests: the active substance content of the first adjuvant was a 50% aqueous solution of sodium salt of alkylbenzenesulfonic acid—10% (HY), whereas the second was from rapeseed oil (natural origin)—85% (OL). Both adjuvants were tested in two concentrations: the first was with the concentration recommended by the manufacturer (100%), whereas the second concentration was 50% of the recommended dose. Two types of water from different sources were used in the tests: the first was from a village in the eastern part of Poland (WS), whereas the second was tap water from the city of Lublin, Poland (WUP). D_v0.1, D_v0.5, or volume median diameter (VMD), D_v0.9, Sauter mean diameter (SMD), relative span (RS), and the droplet size distribution were measured and calculated as characteristics of the droplet size. Results showed that the source of water affected the influence of adding adjuvant to the spray solution. Water from the WS source with adjuvant resulted in a numerical decrease in the D_v0.5 values in the percentage of droplet size range below 150 µm, whereas water from the WUP source resulted in an increase in these values (except when adding the HY adjuvant at 50% concentration). Adjuvant concentration significantly (p < 0.05) influenced the features of D_v0.9, SMD, and RS. Adding the OL adjuvant type numerically decreased the percentage of droplet size below 150 µm, and the D_v0.5 values, but only when the WS water source was used.

The use of worn-out agricultural nozzles in pesticide application has a negative effect on the efficiency and cost of the application process. It also has an effect on environmental pollution due to an excessive amount of pesticide being applied when spraying with worn-out nozzles. In this paper, the resistance to wear of three different internal design hydraulic nozzles was ascertained. Changes in the flow rate and spray distribution as a result of this wear were also investigated. The wear test was done inside a closed system, and it was accelerated using an abrasive material to generate 100 h of wear. The tested nozzles were the Turbo TeeJet (TT)-twin chambered, Turbo Twinjet (TTj60)-dual outlet, and Drift Guard (DG)-pre-orifice. Wear rate, flow rate, and the virtual coefficient of variation (CV_v) were measured at different wear intervals. The results showed that the TTj60 type was the most resistant to wear, followed by the TT type and DG. The latter two types showed an increase in the flow rate only in the first 45 h of wear. Virtual coefficient of variation (CV_v) values were less than 10% after finishing the test (after 100 h of wear) for the three types of nozzles, which are acceptable values according to International Organization for Standardization (ISO) 16122-2, 2015.