Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System
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 h...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | AgriEngineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-7402/7/1/2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589466525499392 |
|---|---|
| author | Renato Herrig Furlanetto Ana Claudia Buzanini Arnold Walter Schumann Nathan Shawn Boyd |
| author_facet | Renato Herrig Furlanetto Ana Claudia Buzanini Arnold Walter Schumann Nathan Shawn Boyd |
| author_sort | Renato Herrig Furlanetto |
| collection | DOAJ |
| description | 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<sup>®</sup> 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 <i>precision</i>, <i>recall</i>, <i>mean average precision</i> (mAP), and F1<i>score</i> 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. |
| format | Article |
| id | doaj-art-4e536bae4cc344ad80f40c6216e1f603 |
| institution | Kabale University |
| issn | 2624-7402 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AgriEngineering |
| spelling | doaj-art-4e536bae4cc344ad80f40c6216e1f6032025-01-24T13:16:11ZengMDPI AGAgriEngineering2624-74022024-12-0171210.3390/agriengineering7010002Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production SystemRenato Herrig Furlanetto0Ana Claudia Buzanini1Arnold Walter Schumann2Nathan Shawn Boyd3Weed Science Laboratory, Gulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USAWeed Science Laboratory, Gulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USACitrus Research and Education Center, University of Florida, Lake Alfred, FL 33850, USAWeed Science Laboratory, Gulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USAIn 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<sup>®</sup> 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 <i>precision</i>, <i>recall</i>, <i>mean average precision</i> (mAP), and F1<i>score</i> 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.https://www.mdpi.com/2624-7402/7/1/2weed controlprecision agricultureYou Only Look Onceobject detection modelvegetable productionsmart sprayer |
| spellingShingle | Renato Herrig Furlanetto Ana Claudia Buzanini Arnold Walter Schumann Nathan Shawn Boyd Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System AgriEngineering weed control precision agriculture You Only Look Once object detection model vegetable production smart sprayer |
| title | Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System |
| title_full | Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System |
| title_fullStr | Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System |
| title_full_unstemmed | Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System |
| title_short | Developing AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System |
| title_sort | developing ai smart sprayer for punch hole herbicide application in plasticulture production system |
| topic | weed control precision agriculture You Only Look Once object detection model vegetable production smart sprayer |
| url | https://www.mdpi.com/2624-7402/7/1/2 |
| work_keys_str_mv | AT renatoherrigfurlanetto developingaismartsprayerforpunchholeherbicideapplicationinplasticultureproductionsystem AT anaclaudiabuzanini developingaismartsprayerforpunchholeherbicideapplicationinplasticultureproductionsystem AT arnoldwalterschumann developingaismartsprayerforpunchholeherbicideapplicationinplasticultureproductionsystem AT nathanshawnboyd developingaismartsprayerforpunchholeherbicideapplicationinplasticultureproductionsystem |