Pattern Matching Best Practices

Best Practices

For testing templates and Pattern Matching parameters (e.g., threshold), use playlists of less than 500 recordings. Do not run a pattern matching job with a large playlist (>500 recordings) until you are confident in the template and parameters.  

Example: A project with 100,000 recordings and 20 species.  We expect that the project may include 3-4 pattern matching training jobs (<500 recordings) per species for testing purposes. Then run 1 final pattern matching job per species with a playlist of 100,000 recordings. 

To create a useful playlist to test the performance of templates and Pattern Matching parameters, we recommend manually validating a subset of recordings. Our science team usually manually inspects and validates species in all recordings from one to two non-consecutive days from each sampling site. 

Tips from Our Team

• The first step in acquiring species information from the audio recordings consists of manually validating a subset of recordings.
• During the manual validation of a subset of recordings, our team also includes Tags named "Good species_name" that identify potential good templates for each focal species. 
  • Explore how to create tags here.
• After manually validating a subset of recordings, you will probably have several recordings with Tags "Good templates_species name" for some species; you can then compare them and select one to be used in the Pattern Matching approach.
• The preliminary species list can offer you a first glimpse of species that occur in your study area and allow you to test the performance of the Pattern Matching models. Once you finish the manual inspection and validation of a subset of recordings, create a playlist with all detected species. 
  • To learn how to create a playlist, visit our tutorials here.
• Then, create a Pattern Matching job that will run over the preliminary species list (< 500 recordings) to test the performance of Pattern Matching models. Once you are confident in the template and Pattern Matching parameters, run a new Pattern Matching over recordings from all sampling sites.
• Our team usually creates a diurnal and nocturnal playlist for diurnal and nocturnal species respectively, for the final analyses. This can reduce processing time and false positives.
• Choosing the proper parameters used in the Pattern Matching templates will depend on your ecological questions. 
  • Using a low threshold, the pattern matching algorithm will detect anything slightly similar to your template.
• Therefore, you will be able to detect natural variations of the species call, but as a tradeoff, you will also detect many false positives.
  • The "Best per Site/Day" filter can be used with a very low threshold to quickly search for occurrences of the target species in each site