Search

In-field weed detection in wheat (Triticum aestivum L.) is challenging due to the occurrence of weeds in close proximity with the crop. The objective of this research was to evaluate the feasibility of using deep convolutional neural networks for detecting broadleaf weed seedlings growing in wheat.The object detection neural networks, including CenterNet, Faster R-CNN, TridenNet, VFNet, and You Only Look Once Version 3 (YOLOv3) were insufficient for weed detection in wheat because the recall never exceeded 0.58 in the testing dataset. The image classification neural networks including AlexNet, DenseNet, ResNet, and VGGNet were trained with small (5500 negative and 5500 positive images) or large training datasets (11 000 negative and 11 000 positive images) and three training image sizes (200 × 200, 300 × 300, and 400 × 400 pixels). For the small training dataset, increasing image sizes decreased the F1 scores of AlexNet and VGGNet but generally increased the F1 scores of DenseNet and ResNet. For the large training dataset, no obvious difference was detected between the training image sizes since all neural networks exhibited remarkable classification accuracies with high F1 scores (≥0.96). All image classification neural networks exhibited high F1 scores (≥0.99) when trained with the large training dataset and the training images of 200 × 200 pixels.CenterNet, Faster R-CNN, TridentNet, VFNet, and YOLOv3 were insufficient, while AlexNet, DenseNet, ResNet, and VGGNet trained with a large training dataset were highly effective for detection of broadleaf weed seedlings in wheat. © 2021 Society of Chemical Industry.

BACKGROUND Italian ryegrass (Lolium perenne ssp. multiflorum) is one of the major winter annual weeds worldwide. In this research, diversity for seed morpho-physiological traits such as seed weight, seed size, awnedness, dormancy, speed of germination, and seed vigor among Italian ryegrass populations collected from the Texas Blacklands region were assessed, and potential association with herbicide resistance was investigated. RESULTS A high degree of diversity was observed among the populations for 100-seed weight (125-256 mg), seed length (4.8-6.6 mm), awn length (0-6 mm), and total seedling length (9-14 cm at 21 days after seed germination). Inter-population range for seed dormancy was higher in the freshly harvested seed (31-85%), which reduced to 18 to 62% at 9 months after harvest. Populations with high initial seed dormancy (> 70% dormancy) released dormancy at a faster rate than the low dormancy group (

Background Weedy sunflower (Helianthus annuus L.) is a troublesome weed in row-crop production fields in South Texas. Populations with suspected resistance to glyphosate were evaluated with 1X and 4X rates (X = 868 g ae ha-1 ) of the herbicide, followed by a dose-response assay of the most resistant population. Molecular studies were conducted to determine if target-site mechanisms were responsible for resistance in these populations. Additionally, field experiments were conducted at two locations (Somerville and Granger, TX) to evaluate the effectiveness of different tank-mix combinations in controlling naturally infesting glyphosate-resistant (GR) weedy sunflower populations in GR corn. Results In a study conducted in the growth chamber, seven of the 11 tested populations survived up to the 4X rate of glyphosate. The most-resistant population (TX15-11) was 29-fold more resistant to glyphosate, compared to the susceptible standard. In resistant populations, 5-21 more copies of the EPSPS gene were observed compared to the susceptible standard. In the field studies, tank-mix applications of glyphosate + halosulfuron-methyl, glyphosate + prosulfuron, glyphosate + a premix of halosulfuron-methyl and dicamba or glyphosate + a premix of diflufenzopyr and dicamba effectively controlled GR weedy sunflower populations. Conclusion Glyphosate-resistance was observed in 81% of the putative resistant weedy sunflower populations tested in this study. Resistance in these populations was conferred primarily by amplification of the EPSPS gene. Effective control of GR weedy sunflower can be achieved by tank-mixes tested in the current study, which provides acceptable levels of crop safety. © 2020 Society of Chemical Industry.