Validating Presence of Species
What is an RFM Training Set?
The training set for RFM consists of two components:
- a training set pattern (region of interest [ROI])
- at least 50 presence and 50 absence species validations
This article covers #2 (how to validate species in your recordings).
Tip: Creating a training set applies to the Random Forest Model only. If you are interested in running Pattern Matching over your data, please reference Creating a Template instead.
How to Validate Species Presence/Absence
1. Go to the project menu and click Explore, then Visualizer.
Explore recordings by selecting a Site and Date or by selecting a playlist (top left corner)
Learn more on the How to Use the Visualizer page.
2. In the left Visualizer menu, click on ‘Species Presence Validation’. Select the appropriate taxonomic group and scroll to where you see your species.
3. Determine if the species of interest is present or absent within the entire 1-minute recording (visually or aurally). To validate the recording, click on ‘Annotation’ to indicate presence or absence of a species’ call.
4. Repeat these steps over a number of recordings. We recommend at least 50 presence and 50 absence validations per species to train Random Forest Models.