| Affiliations: | Aggie Research Mentoring Program |
| Project Leader: | Pavle Pavlovic
Soil and Crop Sciences |
| Faculty Mentor: | Muthu Bagavathiannan, Ph.D. |
|
Meeting Times:
|
TBA |
|
Team Size:
|
3
|
| Open Spots: | 3 |
|
Special Opportunities:
|
Opportunity to explore the field of weed science, as well as agronomy in general, and how field research is conducted. Learning new skills in field data collection, weed identification, weed ecology, herbicide application, UAV and sensor handling. Depending on the level of intelectual contribution to the project there is a possibility of co-authorship, joining our research group in some capacity and a good reference from principal investigator.
|
|
Team Needs:
|
Mandatory Skills: Field Work & Work with Data. Optional Skills: Programming, GIS, Sensors. |
|
Description:
|
The purpose of the project is to better understand the dynamics of weed species in crop production through the lense of machine learning. Application of deep learning for the purposes of weed science is a new area of R&D with many unknowns and knowledge gaps. Therefore, this is an opportunity to participate in the latest cutting edge research in this discipline. The project is multidisciplinary in nature as it not only relies on the well established principles and research practices in weed science, but also on the application of precision technologies such as UAV imaging, satellite imaging, GIS and image analysis. Some trials are still being developed for the project, but at the moment there are two running trials for the summer period at Texas A&M University Farm. The objectives of these trials are two-fold: developing a deep learning model capable of understadning and quantifying weed-crop competition and finding a solution to the occlusion issue on images with both weeds and crops present. Participants will have the opportunity to acquaint themselves with field trial research, data collection, data sorting, data annotation, UAV handling. |