Ana C. Buzanini’s research while affiliated with Florida Gulf Coast University and other places

In plasticulture production, smart spray technology can detect weeds and apply herbicides only where needed in the area between raised, plastic-covered beds (row middle). This technology has the potential to reduce herbicide use and lower input costs. A prototype smart spray system was developed at the Gulf Coast Research and Education Center (GCREC) in Wimauma, FL, that utilizes YOLO-V3 convolutional neural networks to differentiate broadleaf, grass, and nutsedge weeds in row middles. Two sets of field experiments were conducted to determine the efficacy of smart spray technology using a combination of preemergence (PRE) and postemergence (POST) herbicides. All treatments reduced weed density, and targeted applications were as effective as banded treatments. Overall, including a PRE herbicide tended to lower weed density compared to POST applications alone, regardless of application technique. Two banded PRE herbicide applications and two targeted POST applications reduced herbicide use by 52% and 13% compared to banded PRE and POST applications in Experiments 1 and 2, respectively. The reduction from two to one PRE-herbicide applications did not result in an overall herbicide use or cost reduction in Experiment 1, as the decrease in PRE herbicides resulted in increased POST-herbicide usage. In the absence of a banded PRE application, targeted compared to banded POST applications, herbicide usage was reduced by 40 to 67% in Experiment 1 and 79 to 84% in Experiment 2. Smart spray technology is an effective weed management tool for row middles in plasticulture production systems with or without PRE-herbicide applications.

Carolina geranium ( Geranium carolinianum L.) growth in planting holes in commercial strawberry [ Fragaria × ananassa (Weston) Duchesne ex Rozier (pro sp.) [ chiloensis × virginiana ]] fields is a serious problem in Florida. This study aimed to evaluate the effects of different G. carolinianum densities on strawberry growth and yield in plasticulture production systems. Geranium carolinianum densities were 0, 0.4, 0.8, 1.9, 2.7, and 3.8 plants m ⁻² equally distributed on the plastic-mulched bed top within the planting holes. Geranium carolinianum density did not affect plant height; however, seed production and season-end biomass were negatively correlated with density in Season I. There was a negative, linear correlation between weed density and berry yields. With each increase in G. carolinianum per square meter, the total annual yield was lowered by 554 and 935 kg ha ⁻¹ , in Seasons I and II, respectively. Our data clearly indicate that G. carolinianum emerging in the transplant holes of strawberry and competing throughout the season has a significantly negative effect on total berry yield.

In plasticulture production systems, the conventional practice involves broadcasting pre-emergent herbicides over the entire surface of raised beds before laying plastic mulch. However, weed emergence predominantly occurs through the transplant punch-holes in the mulch, leaving most of the applied herbicide beneath the plastic, where weeds cannot grow. To address this issue, we developed and evaluated a precision spraying system designed to target herbicide application to the transplant punch-holes. A dataset of 3378 images was manually collected and annotated during a tomato experimental trial at the University of Florida. A YOLOv8x model with a p2 output layer was trained, converted to TensorRT® to improve the inference time, and deployed on a custom-built computer. A Python-based graphical user interface (GUI) was developed to facilitate user interaction and the control of the smart sprayer system. The sprayer utilized a global shutter camera to capture real-time video input for the YOLOv8x model, which activates or disactivates a TeeJet solenoid for precise herbicide application upon detecting a punch-hole. The model demonstrated excellent performance, achieving precision, recall, mean average precision (mAP), and F1score exceeding 0.90. Field tests showed that the smart sprayer reduced herbicide use by up to 69% compared to conventional broadcast methods. The system achieved an 86% punch-hole recognition rate, with a 14% miss rate due to challenges such as plant occlusion and variable lighting conditions, indicating that the dataset needs to be improved. Despite these limitations, the smart sprayer effectively minimized off-target herbicide application without causing crop damage. This precision approach reduces chemical inputs and minimizes the potential environmental impact, representing a significant advancement in sustainable plasticulture weed management.

Goosegrass [ Eleusine indica (L.) Gaertn.] is one of the most problematic weeds in plasticulture strawberry [ Fragaria × ananassa (Weston) Duchesne ex Rozier (pro sp.) [ chiloenis × virginiana ]] production systems in Florida. A 2-yr trial was implemented to evaluate the effects of different E. indica densities on strawberry growth and yield. Eleusine indica densities evaluated were 0, 0.4, 0.8, 1.9, 2.7, and 3.8 plants m ⁻² equally distributed on the plastic-mulched bed top within the strawberry transplant holes. Eleusine indica density did not affect E. indica height or biomass. However, E. indica seed production was positively correlated with E. indica density in Season 1 and negatively correlated with E. indica density in Season 2. A negative linear regression was observed between E. indica density and strawberry yield in both seasons. For each increase in E. indica plants per square meter, strawberry yield was reduced by 316 and 2,356 kg ha ⁻¹ for Seasons 1 and 2, respectively. Our results highlight the importance of achieving adequate E. indica management to minimize yield losses.

Smart spray technology developed at the University of Florida was designed to reduce off-target applications when applying postemergence (POST) herbicides for weed control in plasticulture systems. A trial was conducted in the fall of 2021 and spring of 2022 to evaluate smart spray technology in row middles in a banana pepper field at the Gulf Coast Research and Education Center in Balm, FL. The objective of this study was to evaluate the efficacy of targeted POST-herbicide applications in plasticulture pepper row middles in the presence or absence of a pre-emergent (PRE) herbicide. Flumioxazin reduced broadleaf and overall weed densities in both seasons and lowered grass density in the spring. Two targeted applications reduced the nutsedge density in spring compared to the two banded applications. No significant pepper damage was observed in any treatments. Applied POST herbicide volume following PRE-herbicide was reduced by 84% and 54% for fall and spring respectively. In the absence of a PRE herbicide, targeted applications reduced POST-herbicide volumes by 30% and 45% for fall and spring respectively. No reduction in weed control or pepper yield was observed when comparing targeted with banded applications. Overall, the use of smart spray technology for POST herbicides in row middles reduced applied spray volume with no reduction in weed control, significant injuries on pepper, or negative effects on yield.

Postemergence herbicides to control weeds in the space between raised, plastic-covered beds in plasticulture production systems are typically banded and herbicides are applied to weeds as well as where weeds do not occur. To reduce the incidence of off-targeted applications, the University of Florida developed smart spray technology for row middles in plasticulture systems. The technology detects weed categories and applies herbicides only where they occur. Field experiments were conducted at the Gulf Coast Research and Education Center in Balm, FL, in the Fall 2021 and Spring 2022. The objective was to evaluate the efficacy of postemergence applications of diquat and glyphosate in row middles in jalapeno pepper fields when banded or applied with smart spray technology. The overall precision of the weed detection model was 0.92 and 0.89 for fall and spring respectively. The actuation precision achieved was 0.86 and 1 for fall and spring respectively. No significant differences were observed between banded and targeted applications either with glyphosate or diquat in terms of broadleaf, grass, and nutsedge weed density. No significant pepper damage was observed with either herbicides or application techniques. The smart spray technology reduced herbicide application volume by 26% and 42% for fall and spring respectively, with no reduction in weed control or pepper yield compared to a banded application. Overall, the smart spray technology reduced the herbicide volume applied with no reductions in weed control and no significant effects on crop yield.

Preemergence (PRE) herbicides are often banded over the entire top of raised beds for broadleaf and grass control in plasticulture vegetable production systems. However, broadleaf and grass weeds only emerge from the planting holes and tears in the plastic mulch. Banded application results in herbicides applied where no holes occur and therefore where they are not needed. Our objective is to identify herbicides that do not harm transplanted crops when directed at transplant holes post-transplant (POST) with the aim to reduce off-target applications. Therefore, we evaluated tomato and pepper tolerance to PRE herbicides applied to transplant holes 2 weeks after transplant and the subsequent effects on crop tolerance and weed density. Halosulfuron, S -metolachlor, metribuzin, and pendimethalin did not injure tomato transplants, reduce height, or reduce yield. Fomesafen caused some tomato injury (7%) but had no effect on other measured parameters in Trial I. All PRE herbicides injured peppers (≥19%) though no effect on yield was observed. Overall, halosulfuron, S -metolachlor, metribuzin, and pendimethalin can be safely applied to tomato transplant holes two weeks after transplant with no significant crop injury nor effects on final yield, but none of the evaluated herbicides are safe for use in pepper.