AI-Assisted Sturgeon Sex Determination

Jan 15, 2024 · 1 min read
project

Overview

This project develops artificial intelligence and machine learning approaches to revolutionize sex determination in sturgeon aquaculture, dramatically reducing costs and improving sustainability of caviar production.

Funding: ~$465,000 USDA NIFA Western Regional Aquaculture Center (2024-2027) - Active Role: Principal Investigator

The Problem

Sturgeon aquaculture faces a critical challenge: females (caviar producers) cannot be reliably distinguished from males until 7-10 years of age, leading to massive resource waste and economic inefficiency.

Our Approach

  • AI-Based Computer Vision: Non-invasive imaging with deep learning models
  • Genomic Markers: Sex-specific DNA sequence identification
  • Automation & Integration: Scalable deployment across facilities

Progress

  • Achieved 90%+ accuracy in preliminary sex classification models (improved from initial 76%)
  • Developing robust pipelines for real-world aquaculture deployment
  • Building partnerships with sturgeon farms in California and Idaho

Collaborators

  • UC Davis (Department of Animal Sciences, Dr. Jackson Gross)
  • University of Washington Friday Harbor Laboratories (Dr. Adam Summers)
  • Industry partners: Sturgeon growers in California and Idaho

Expected Impact

  • Reduce operational costs by 30-50% through early sex identification
  • Lower environmental footprint of caviar production
  • Open-source framework for broader aquaculture applications
  • Contribute to sustainable food production

Press Coverage

Featured in SDSC, ACCESS-CI, SeafoodSource, and Hatchery International (2025).

Machine Learning Computer Vision Aquaculture AI Sustainability
Edwin Solares
Authors
Edwin Solares (he/him)
Lecturer in Computer Science & Data Science
I am a computational biologist and data scientist bridging artificial intelligence, evolutionary genomics, and climate-resilient agriculture. My research leverages cutting-edge machine learning and bioinformatics to address global food security challenges in the face of rapid climate change. With publications in high-impact journals including Nature Plants, PNAS, and Genome Research (h-index: 7), I develop tools and methods that advance both computational science and real-world applications.