IA-2026-0091
Automatic detection of unidentified fish sounds
Pilot Ecosystems and Oceans Science
Description of the initiative
This completed project used Random Forests and Convolutional Neural Networks (CNN) algorithms trained on manually detected fish sounds to detect fish sounds collected on a passive acoustic monitoring project. The result is an easy-to-use, open-source software called FishSoundFinder, implemented with the CNN detector.
Strategic alignment
- —
Contacts
- Subject matter expert
- Winegardner, Amanda
Lifecycle
-
Ideation
Stage status : Completed
August 28, 2026 August 28, 2026
-
Assessment
Stage status : Not applicable
-
Approved
Stage status : Not applicable
-
Development
Stage status : Not applicable
-
Pilot
Stage status : In progress
August 28, 2026
-
Production
Stage status : Upcoming
-
Archived
Stage status : Upcoming
Schedule for this initiative
- Completed
- In progress
- Planned
- Not applicable
- Today
Change log (12 entries)
Public history of this initiative's key events. The team's internal exchanges are not shown.
-
Stage change
etape_actuelle_id
-
Stage change
pilote.statut
-
Stage change
pilote.date_reelle_debut
-
Stage change
developpement.statut
-
Stage change
approuvee.statut
-
Stage change
evaluation.statut
-
Stage change
ideation.statut
-
Stage change
ideation.date_reelle_fin
-
Stage change
etape_actuelle_id
-
Stage change
ideation.statut
-
Stage change
ideation.date_reelle_debut
-
Created