Summary:-PhD Candidate in Marine Science with Dave Johnston in the Marine Robotics and Remote Sensing Center at Duke University
- oceanographic remote sensing of physical-biological interactions
- earth system science
- machine learning approaches to remote sensing analysis
- the intersection of ocean and planetary science
- drones and autonomy for ocean science
- being outside as much as possible
Work and Focus
I'm currently a PhD student with Dave Johnston
in the Marine Robotics and Remote Sensing Lab at the Duke University Marine Laboratory
and a Future Investigator in NASA Earth and Space Science and Technology (FINESST).
My doctoral research focuses on satellite and drone based remote sensing of oceans and coasts. My work aims to understand spatial and temporal variability of ocean biology and ecology. Working at the confluence of remote sensing, data science, and biological oceanography I lean heavily on machine learning and scientific computing tools for parsing large amounts of remotely sensed data and connecting satellite, drone, and in-situ oceanographic monitoring. I'm particularly interested in tools and research that will be relevant for Earth science and for exploring other bodies within our solar system.
Before joining the Duke Marine Lab, I worked at Harvard University as a research technician in the deep-sea focused Girguis Lab, served a year and a half as Chief Technology Officer at WayPaver Foundation, and spent time at Moon Express as a Software Engineer developing their ground data systems and engineering team tools. I graduated from the University of North Carolina as a Morehead-Cain Scholar with a degree in Computer Science where I started UNC Students for the Exploration and Development of Space and researched computer vision.
Open Source Coding Projects
Quick overview of open-source projects.
Open source code and data for the manuscript "Temporally Generalizable Land Cover Classification: A Recurrent Convolutional Neural Network Unveils Major Coastal Change through Time" currently under review at Remote Sensing of Environment.
Tools and algorithms for drone and satellite based ocean color science. A much larger repo for full processing of drone-based multispectral imagery to ocean color is in development and will be released openly soon.
Open Geo Tutorial A series of labs on remote sensing and GIS methodologies using open source software in python.
Deep Learning for Ecology Educational Resources on Neural Networks for Ecology and Remote Sensing
Scientific Computing Template A stock scientific computing and deep learning environment for analysis of remote sensing data using docker conda, and most common tools for machine learning in remote sensing such as keras, scikit-learn, xarray, rasterio, etc.
Open source code and data for the manuscript "Drones and Convolutional Neural Networks Facilitate Automated and Accurate Cetacean Species Identification and Photogrammetry."
Summary of recent projects. Full list of journal and conference papers can be found here on Google Scholar.
Fine scale ocean observations to better understand physical biological interaction across the Gulf Stream front
Characterizing the distribution of productivity and diversity across the Gulf Stream front below the scale of a few kilometers to better understand the dynamics of the ecological and physical environment at this scale.
Ocean color algorithm development for drone-based multi- and hyperspectral imagers
Working on more robust ccean color from unoccupied aircraft systems including sensor setup, sunglint and reflected skylight corrections, and chla retrieval algorithms.
Satellite analysis of Gulf Stream physical biological interactions
Satellite analysis of long term SST and chla across the Gulf Stream. Above images are GOES hourly SST at 1km resolution and ECOSTRESS-based SST at 70m.
Deep learning for remote sensing analysis
This encompasses a range of deep learning projects from object detection for wildlife applications to change detection across planetary bodies to land cover mapping.
Some Fieldwork Photos
The Duke Marine Lab from a drone's point of view.
Duke's R/V Shearwater on a student cruise where we tested our initial multispectral imager based ocean color approach.
In Nags Head Woods, NC flying coastal surveys to look at fine-scale change in maritime forests.