Proceedings
Authors
| Filter results5 paper(s) found. |
|---|
1. Three Years of On-Farm Evaluation of Dynamic Variable Rate Irrigation: What Have We Learned?This paper will present a dynamic Variable Rate Irrigation System developed by the University of Georgia. The system consists of the EZZone management zone delineation tool, the UGA Smart Sensor Array (UGA SSA) and an irrigation scheduling decision support tool. An experiment was conducted in 2015, 2016 and 2017 in two different peanut fields to evaluate the performance of using the UGA SSA to dynamically schedule Variable Rate Irrigation (VRI). For comparison reasons strips were designed within... V. Liakos, W. Porter, X. Liang, M. Tucker, A. Mclendon, C. Perry, G. Vellidis |
2. Management Zone Delineation for Irrigation Based on Sentinel-2 Satellite Images and Field PropertiesThis paper presents a case study of the first application of the dynamic Variable Rate Irrigation (VRI) System developed by the University of Georgia to cotton. The system consists of the EZZone management zone software, the University of Georgia Smart Sensor Array (UGA SSA) and an irrigation scheduling decision support tool. An experiment was conducted in 2017 in a cotton field to evaluate the performance of the system in cotton. The field was divided into four parallel strips. All four strips... V. Liakos, G. Vellidis, L. Lacerda, W. Porter, M. Tucker, C. Cox |
3. Generative Modeling Method Comparison for Class Imbalance CorrectionAn image dataset, for use in object detection of hay bales, with over 6000 images of both good and bad hay bales was collected. Unfortunately, the dataset developed a class imbalance, with more good bale images than bad bales. This dataset class imbalance caused the bad bale class to over train and the good bale class to under train, severely impacting precision, and recall. To correct this imbalance and provide a comparison of differing generative modeling methods; three different... B. Vail, Z. Oster, B. Weinhold |
4. Enhancing Weed Detection in Corn Crops Through Attention-based Models and Curated DatasetsWeed infestation is one of the leading causes of global agricultural productivity losses, directly impacting production costs, environmental sustainability, and food security. In precision agriculture, automated weed detection from aerial imagery enables site-specific herbicide application, reducing chemical overuse and environmental impact. Deep learning-based computer vision techniques have been widely adopted for this purpose, with Convolutional Neural Networks (CNNs) historically dominating... T.M. Martins, E.C. Tetila, J.G. Barbedo, J.C. Felipe, L. Zhao |
5. Challenges in Integrating Digital Agriculture SolutionsAdvances in digital agriculture have increased the supply of solutions to improve the management of agricultural activity. However, the increasing number of solutions in quantity and variety also imposes barriers to their adoption by small and medium-sized family farmers reasoned by higher exposition to technical and financial limitations. High cost, low digital literacy, and little perception of the usefulness are some of the obstacles. These can be further exacerbated if producers need to... J. Da Silva, S.R. Evangelista, J.G. Barbedo, L.A. Romani |