United KingdomPublic sector2026 – ongoingScottish Environment Protection Agency
Machine-learning assessment of seabed health beneath fish farms
SEPA adopted a seabed compliance assessment model trained on 950 samples
Problem
Fish waste and uneaten feed could damage seabed habitats beneath farms. Traditional assessment required specialist taxonomists and could take up to three months.
Approach
SEPA formally adopted eDNA-2-IQI to support statutory compliance assessments. SAMS led the research with regulatory and industry partners. The method combined bacterial DNA analysis with a random forest trained to predict sediment health.
Results
Takeaway
The new method changed the evidence available for compliance decisions. SEPA said the environmental standards and its regulatory role remained unchanged.
Categories
- Industry
- Public sector
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Vendor case study
Sources
Source summaries
The research partner reported SEPA's formal adoption of eDNA-2-IQI for compliance assessment. It described training on 950 samples and results available within weeks, with comments from SEPA about the regulatory use.
Full details are in the original sources.