Shark Detector, sharkPulse tooling, eDNA and spatial-modeling code from my PhD and independent research.
- Shark-Detector Shark classification model
- jj-website This is Jeremy's professional website repository
- kayak-pi A fish finder for any kayak
Marine Data ScientistML / AI EngineerConservationist
I build computer vision, eDNA, and statistical tools that count and track marine life without ever touching it.
Background: drone survey frame with automated shark tracks, Beneath The Waves
About
I'm a data scientist and machine-learning engineer at NOAA's Northeast Fisheries Science Center in Woods Hole, where I turn millions of seafloor images into abundance estimates for stock assessments. My work sits where field ecology meets production software: detection and tracking models for sharks, scallops and deep-sea fauna; eDNA assays that find endangered white sharks from a liter of seawater; and the cloud pipelines that make all of it run at survey scale.
Selected work
HabCam imagery: NOAA NEFSC object detection · bias correction · GCP
Read more
Photo: Beneath The Waves image classification · video AI · R / Flask API
Read more
eDNA · particle tracking · citizen science
Read more
Photo: Beneath The Waves genomics · deep-sea video · open biodiversity data
Read more
Photo: sharkPulse record archive NLP · data engineering · Shiny
Read moreSelected publications
Accelerating shark video surveys with AI and automated workflows
Ecological Informatics
Automatically counting and measuring Atlantic sea scallops (Placopecten magellanicus) from underwater imagery with object detection and bias-correction
Ecological Informatics
Addressing distributional and taxonomic uncertainty in the deep-sea giant isopod genus Bathynomus with an integrated observational and molecular framework
Deep Sea Research Part I: Oceanographic Research Papers
From data deficient to big data in shark conservation
Fish and Fisheries
Shark detection and classification with machine learning
Ecological Informatics
Open source
Shark Detector, sharkPulse tooling, eDNA and spatial-modeling code from my PhD and independent research.
Computer vision and cloud pipelines for HabCam optical surveys and stock-assessment science.
In the news
Contact