Bio
John is a R&D Associate Staff Member in the Biosciences Division at Oak Ridge National Laboratory.
His research focuses on the development and subsequent application of mathematical, computational, and statistical methods to biological and environmental datasets in order to yield new insights into complex biological systems.
Approaches include scientific machine and deep learning (e.g., neural networks, explainable-AI, and computer vision), graph and network theory (e.g., unsupervised clustering, longitudinal analysis, and geometric deep learning), and mathematical modeling (e.g., ODEs, PDEs, and nonlinear optimization) to address questions across:
- Biological scales ranging from cells (virus and microbes) to organisms (plants and humans) to the global ecosystem (communities and environments).
- Data modalities ranging from structured (RGB and hyperspectral) to unstructured (point clouds and graphs) to sequential (time series and video).
- Computing systems ranging from local (Linux, MacOS, Windows) to leadership-class systems (Andes, Summit, Perlmutter, and Frontier).
John leads multiple projects related to plant phenotyping and global climate analysis, resulting in a number of accomplishments (e.g., the fastest scientific computation in human history and reaching human-level segmentation accuracy using fewer than 10 training images) and funding opportunities (e.g., a Laboratory Directed Research and Development award).
He actively mentors graduate students and summer interns and collaborates on multidisciplinary and multi-institutional projects across a wide network of collaborators from around the world.
John earned his MS and PhD in Applied Mathematics from North Carolina State University and a BS in Computational and Applied Mathematics from East Tennessee State University.
Awards
- People's Choice Award, ORPA Research Symposium, ORNL, 2023
- LDRD, AI-enabled association of plant physiology and phenotypes, ORNL, 2022-2023
Professional Service
- Code release: Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa
- Data release: Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa
- Data release: Climatic clustering and longitudinal analysis with impacts on food, bioenergy, and pandemics