Deep learning for image-based detection of weeds from emergence to maturity in wheat fields
Effective weed control in wheat (Triticum aestivum L.) fields is crucial for optimizing production and ensuring food security in semi-arid regions. The implementation of deep learning for weed detection could enable precise weed management, leading to enhanced wheat yield, increased income for growe...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375524001576 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850108311423156224 |
|---|---|
| author | Mustafa Guzel Bulent Turan Izzet Kadioglu Alper Basturk Bahadir Sin Amir Sadeghpour |
| author_facet | Mustafa Guzel Bulent Turan Izzet Kadioglu Alper Basturk Bahadir Sin Amir Sadeghpour |
| author_sort | Mustafa Guzel |
| collection | DOAJ |
| description | Effective weed control in wheat (Triticum aestivum L.) fields is crucial for optimizing production and ensuring food security in semi-arid regions. The implementation of deep learning for weed detection could enable precise weed management, leading to enhanced wheat yield, increased income for growers through targeted herbicide use, and a reduced environmental footprint associated with herbicide application. Charlock mustard (Sinapis arvensis L.) [CM], creeping thistle (Cirsium arvense (L.) Scop) [CT], and forking larkspur (Consolida regalis Gray) [FL]) are among the most invasive weed species in wheat fields. Effective management of these weeds is essential to ensure optimal wheat productivity in the semi-arid regions. To detect weeds, an unmanned arial vehicle was used to collect images and videos from 185 wheat fields in Tokat, Turkey. The images were collected from five phenological periods of each species including seedling, rosette, vegetative, flowering, and fruiting (in total 15 classification process). These stages are either important for timely weed control or essential for understanding weed pressure threshold, the potential for increasing weed seedbank increase, and identifying herbicide resistant weeds. A total of 145,792 objects were labeled in the images to create the dataset, divided into 80 % for training + validation and 20 % for testing. The dataset was used with the YOLOv5 (You Only Look Once) deep learning architecture. The YOLOv5 was the newest YOLO model during this study carried out. All neural networks provided by YOLOv5 (nano, small, medium, large, and xlarge) were trained and the Precision, Recall, F-1 Score, and AUC (Area under the Curve) performances of the neural networks were evaluated. The YOLOv5s (small) was the most precise neural network in detecting weeds regardless of the species. In contrast, nano was the least precise neural network in detecting each weed species. For CT, when small neural network was used, precision of detection ranged from 0.87 (fruit stage) to 0.96 (rosette and vegetative stages). For, forking larkspur, the best neural network was achieved with YOLOv5 small and the precision ranged from 0.45 (fruit stage) to 0.93 (vegetative stage). Using YOLOv5 small in Charlock mustard, the most precise detection occurred at seedling, rosette, and vegetative stages (with precision of 0.96) and the least precise detection was recorded at the fruit stage (0.81). Other performance evaluations (Recall, F-1 Score, and AUC) were in agreement with those of Precision. Our results indicated that by using YOLOv5 small neural network, all three weed species could be detected at all growth stages with the precision of 0.86 with the exception of fruit stage. Future research should (1) focus on assessing YOLOv5 small neural network with the newest versions of YOLO and also (2) evaluate this neural network for detecting weed species in wheat fields to allow for improved weed control and future recommendations. |
| format | Article |
| id | doaj-art-78deb902894643ec85b33681a1e4e48d |
| institution | OA Journals |
| issn | 2772-3755 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-78deb902894643ec85b33681a1e4e48d2025-08-20T02:38:23ZengElsevierSmart Agricultural Technology2772-37552024-12-01910055210.1016/j.atech.2024.100552Deep learning for image-based detection of weeds from emergence to maturity in wheat fieldsMustafa Guzel0Bulent Turan1Izzet Kadioglu2Alper Basturk3Bahadir Sin4Amir Sadeghpour5Tokat Gaziosmanpasa University, Faculty of Agriculture, 60150, Tokat, Türkiye; School of Agricultural Sciences, Southern Illinois University, Carbondale, IL 62901, USA; Corresponding author.Tokat Gaziosmanpasa University, Faculty of Engineering and Natural Sciences, 60150, Tokat, TürkiyeTokat Gaziosmanpasa University, Faculty of Agriculture, 60150, Tokat, TürkiyeErciyes University, Faculty of Engineering, 38280, Kayseri, TürkiyeSakarya University of Applied Science, Faculty of Agriculture, 54440, Serdivan, Sakarya, TürkiyeSchool of Agricultural Sciences, Southern Illinois University, Carbondale, IL 62901, USAEffective weed control in wheat (Triticum aestivum L.) fields is crucial for optimizing production and ensuring food security in semi-arid regions. The implementation of deep learning for weed detection could enable precise weed management, leading to enhanced wheat yield, increased income for growers through targeted herbicide use, and a reduced environmental footprint associated with herbicide application. Charlock mustard (Sinapis arvensis L.) [CM], creeping thistle (Cirsium arvense (L.) Scop) [CT], and forking larkspur (Consolida regalis Gray) [FL]) are among the most invasive weed species in wheat fields. Effective management of these weeds is essential to ensure optimal wheat productivity in the semi-arid regions. To detect weeds, an unmanned arial vehicle was used to collect images and videos from 185 wheat fields in Tokat, Turkey. The images were collected from five phenological periods of each species including seedling, rosette, vegetative, flowering, and fruiting (in total 15 classification process). These stages are either important for timely weed control or essential for understanding weed pressure threshold, the potential for increasing weed seedbank increase, and identifying herbicide resistant weeds. A total of 145,792 objects were labeled in the images to create the dataset, divided into 80 % for training + validation and 20 % for testing. The dataset was used with the YOLOv5 (You Only Look Once) deep learning architecture. The YOLOv5 was the newest YOLO model during this study carried out. All neural networks provided by YOLOv5 (nano, small, medium, large, and xlarge) were trained and the Precision, Recall, F-1 Score, and AUC (Area under the Curve) performances of the neural networks were evaluated. The YOLOv5s (small) was the most precise neural network in detecting weeds regardless of the species. In contrast, nano was the least precise neural network in detecting each weed species. For CT, when small neural network was used, precision of detection ranged from 0.87 (fruit stage) to 0.96 (rosette and vegetative stages). For, forking larkspur, the best neural network was achieved with YOLOv5 small and the precision ranged from 0.45 (fruit stage) to 0.93 (vegetative stage). Using YOLOv5 small in Charlock mustard, the most precise detection occurred at seedling, rosette, and vegetative stages (with precision of 0.96) and the least precise detection was recorded at the fruit stage (0.81). Other performance evaluations (Recall, F-1 Score, and AUC) were in agreement with those of Precision. Our results indicated that by using YOLOv5 small neural network, all three weed species could be detected at all growth stages with the precision of 0.86 with the exception of fruit stage. Future research should (1) focus on assessing YOLOv5 small neural network with the newest versions of YOLO and also (2) evaluate this neural network for detecting weed species in wheat fields to allow for improved weed control and future recommendations.http://www.sciencedirect.com/science/article/pii/S2772375524001576Weed detectionDeep learningGrowing stagesWheatYOLOv5 |
| spellingShingle | Mustafa Guzel Bulent Turan Izzet Kadioglu Alper Basturk Bahadir Sin Amir Sadeghpour Deep learning for image-based detection of weeds from emergence to maturity in wheat fields Smart Agricultural Technology Weed detection Deep learning Growing stages Wheat YOLOv5 |
| title | Deep learning for image-based detection of weeds from emergence to maturity in wheat fields |
| title_full | Deep learning for image-based detection of weeds from emergence to maturity in wheat fields |
| title_fullStr | Deep learning for image-based detection of weeds from emergence to maturity in wheat fields |
| title_full_unstemmed | Deep learning for image-based detection of weeds from emergence to maturity in wheat fields |
| title_short | Deep learning for image-based detection of weeds from emergence to maturity in wheat fields |
| title_sort | deep learning for image based detection of weeds from emergence to maturity in wheat fields |
| topic | Weed detection Deep learning Growing stages Wheat YOLOv5 |
| url | http://www.sciencedirect.com/science/article/pii/S2772375524001576 |
| work_keys_str_mv | AT mustafaguzel deeplearningforimagebaseddetectionofweedsfromemergencetomaturityinwheatfields AT bulentturan deeplearningforimagebaseddetectionofweedsfromemergencetomaturityinwheatfields AT izzetkadioglu deeplearningforimagebaseddetectionofweedsfromemergencetomaturityinwheatfields AT alperbasturk deeplearningforimagebaseddetectionofweedsfromemergencetomaturityinwheatfields AT bahadirsin deeplearningforimagebaseddetectionofweedsfromemergencetomaturityinwheatfields AT amirsadeghpour deeplearningforimagebaseddetectionofweedsfromemergencetomaturityinwheatfields |