Dr. Hoarfrost studies the interactions between biological systems and their environment using deep learning and machine learning techniques. She also develops high-throughput experimental techniques to test hypotheses and create deep learning-scale datasets, and deploys technologies to demonstrate their performance in the field. She is particularly interested in microbial drivers of the global carbon cycle, its impact on climate and the marine ecosystem, and marine biotech. Her research topics include:

• Foundation models and transfer learning for biology
• Active learning and self-driving labs
• Deep representation learning for microbial communities and emergent phenotypes
• Characterizing uncharacterizable microbes and functions ('microbial dark matter')
• Identifying key biomarkers of the marine carbon cycle and ecosystem-level microbial phenotypes
• Modeling the biological carbon pump
• Identifying/synthesizing marine microbes for commercially relevant sustainable materials

The Hoarfrost lab is currently recruiting, we encourage interested students to reach out about opportunities. 

Dr. Jaime Camelio is currently the Associate Dean for Research, Innovation, and Entrepreneurship in the College of Engineering at the University of Georgia. From 2008 to 2019, he was a professor for Advanced Manufacturing in the Grado Department of Industrial and Systems Engineering at Virginia Tech. He served as Chief Technology Officer at the Commonwealth Center for Advanced Manufacturing (CCAM) from 2016-2019. Dr. Camelio obtained his B.S. and M.S. in Mechanical Engineering from the Catholic University of Chile in 1994 and 1995, respectively. In 2002, he received his Ph.D. from the University of Michigan. His professional experience includes working as a consultant in the Automotive/Operations Practice at A.T. Kearney Inc. He has extensive experience in operation management in manufacturing environments including industry 4.0 transformation, production control, and lean manufacturing. His research interests are in innovation education, intelligent manufacturing, and cyber-physical security. He has authored or co-authored more than 120 technical papers. He teaches undergraduate and graduate courses related to design, manufacturing processes, manufacturing systems, and data mining.

Dr. Guoming Li has developed and utilized various machine and deep learning models to detect and evaluate animal behavior, welfare, body condition, phenotyping, health status, productivity, and environment. He has embedded these models into various precision agriculture tools (i.e., robotics, radio frequency identification system, computer vision system, sound recognition system, accelerometer, infrared thermography, and 3D sensing device) to support precision management in animal production. The animal species include poultry, swine, and cattle. His research also covered five major deep learning-based computer vision tasks, which are image classification, object detection, semantic/instance segmentation, keypoint/pose estimation, and tracking.