Weed detection is critical for precision agriculture, enabling targeted herbicide application to reduce costs and enhance crop health. This study utilized UAV-acquired RGB imagery from cotton fields to develop and evaluate deep learning models for weed detection. As sustainable resource management gains importance in rainfed agricultural systems, precise weed identification is essential to optimize yields and minimize herbicide use. However, distinguishing weeds from crops in complex field environments remains challenging due to their visual similarity. This research employed YOLOv7, YOLOv7-w6, and YOLOv7-x models to detect and classify weeds in cotton fields, using a dataset of 9249 images collected under real field conditions. To improve model performance, we enhanced the annotation process using LabelImg and Roboflow, ensuring accurate separation of weeds and cotton plants. Additionally, we fine-tuned key hyperparameters, including batch size, epochs, and input resolution, to optimize detection performance. YOLOv7, achieving the highest estimated accuracy at 83%, demonstrated superior weed detection sensitivity, particularly in cluttered field conditions, while YOLOv7-x with accuracy at 77% offered balanced performance across both cotton and weed classes. YOLOv7-w6 with accuracy at 63% faced difficulties in distinguishing features in shaded or cluttered soil regions. These findings highlight the potential of UAV-based deep learning approaches to support site-specific weed management in cotton fields, providing an efficient, environmentally friendly approach to weed management.

Peer-led Team Learning (PLTL) is a model of instruction and learning that has been used to address low success rates in various science, technology, engineering, and mathematics (STEM) courses and other fields in higher education. (1) While research conveying the efficacy of this model of instruction remains mixed, this project sought to add to the body of knowledge communicating the benefits of PLTL for STEM achievement. This study examined the experiences of STEM community college transfer students’ engagement in PLTL within their major course of study when a suite of supports was provided. (2) Specifically, study participants were enrolled in degree programs at a four-year rural, regional university in the engineering, computer science, and mathematics (ECSM) fields and were provided social, financial, and academic assistance. Qualitative analysis of the data revealed that with a PLTL component, community college transfer students were more likely to participate, engage, and perform better in coursework given the additional supports. (3) Study participants indicated the community of learners created through PLTL was a primary motivator for continued engagement and progress towards ECSM degree attainment. (4) Implications for practice extend to engagement and retention efforts of STEM students from the community college population

The dataset consists of drone images of cotton fields which were created to aid precision agriculture and machine learning-based weed detection research. The main goal is to enable the creation of object detection models for crop-weed differentiation while providing a standard for model evaluation. The dataset release serves two purposes: it supports the advancement of automated agricultural monitoring and sustainable farming practices, and it adds to the expanding research on AI solutions for agricultural productivity and environmental management.

Weed detection is an important part of precision agriculture because it allows farmers to manage weeds more efficiently and reduce unnecessary herbicide use. With the use of UAVs, it is now possible to capture high-resolution images of agricultural fields, but identifying weeds from these images is still challenging due to complex backgrounds, lighting variations, and the visual similarity between crops and weeds. In this study, an improved YOLOv7-based approach is developed to address these challenges using UAV imagery collected from rainfed cotton fields in the Texas Panhandle. The original dataset consisted of high-resolution UAV images, which were divided into smaller patches and manually annotated to label weed and cotton classes. After cleaning the dataset and applying simple augmentation techniques, a total of 8396 images were used for training and testing. To improve detection performance, two modifications were introduced: Convolutional Block Attention Module (CBAM) to help the model focus on important features and Bidirectional Feature Pyramid Network (BiFPN) to improve how information is shared across different scales. Three models—YOLOv7-CBAM, YOLOv7-BiFPN, and the combined CB-YOLOv7—were evaluated. The results show that CBAM helps detect more weed instances, BiFPN reduces false detections, and the combined model gives the best overall performance, achieving an mAP@0.5 of 0.89 and an F1-score of 0.84. Overall, the study shows that improving both the dataset and the model can lead to more reliable weed detection under real field conditions. The proposed approach can be useful for identifying weeds in cotton fields using UAV imagery and can support better crop management and more efficient use of herbicides in precision agriculture.