Enabling AI for citizen science in fish biology

Science Center Objects

Artificial Intelligence (AI) is revolutionizing ecology and conservation by enabling species recognition from photos and videos. Our project evaluates the capacity to expand AI for individual fish recognition for population assessment. The success of this effort would facilitate fisheries analysis at an unprecedented scale by engaging anglers and citizen scientists in imagery collection. This project is one of the first attempts to apply AI towards fish population assessment with citizen science.

Our study seeks to apply technological advances in Artificial Intelligence (AI), machine learning, and high-performance computing to enable new methods for fish biology and population assessment. We propose 3 main research objectives: (1) assemble and annotate fish imagery for AI training data, (2) develop and evaluate CNN models for classification of species and individuals, (3) evaluate the capacity for AI application in riverine fish population assessment based on estimated error rates. We are using imagery of wild brook trout (Figure 1) and other species to train and test individual-recognition models. This modeling approach could enable anglers to contribute to quantitative fish population assessments based on imagery of fish they encounter. This project is supported by the USGS Community for Data Integration.

brook trout

Example of brook trout imagery for individual-recognition analysis with Artificial Intelligence. Individually-diagnostic pigmentation patterns including spots and dorsal vermiculation may enable individual recognition. Photo: LSC Stream Lab (Hitt). (Public domain.)

Role Name Affiliation Expertise
Co-PI Natalya Rapstine USGS Science Analytics and Synthesis, Advanced Research Computing AI, HPC
Collaborator Mona Apogee Apogee Engineering AI, HPC
  Jeff Falgout USGS Science Analytics and Synthesis, Advanced Research Computing AI, HPC
  Ben Letcher USGS Leetown Science Center Fish population modeling,
Ecological applications of AI 
  Nicholas Polys Virginia Tech, Advanced Research Computing AI, HPC, web3D
  Sophia Liu USGS Science and Decisions Center (SCD), North Atlantic Appalachian Region Citizen science,
open innovation expertise
  Sean Simmons Angler’s Atlas, Inc.
(Edmonton, Canada)
Citizen science, crowdsourcing
  Bryan Kelly White Fly Outfitters
(Harpers Ferry, WV)
Angler outreach
  Josh Henesy Maryland Department of Natural Resources Smallmouth bass sourcing,
state coordination
  Andy Royle USGS Patuxent Wildlife Research Center AI applications,
USGS Powell Center co-PI
  Ellen Ditria Australian Rivers Institute, Griffith University AI, fish ecology
  Jason Burton USGS Eastern Regional Communications Team Press release,
social media coordination