Supplementary material from "Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics"

Machine learning has the potential to revolutionize passive acoustic monitoring (PAM) for ecological assessments. However, high annotation and compute costs limit the field’s adoption. Generalizable pretrained networks can overcome these costs, but high-quality pretraining requires vast annotated libraries, limiting its current application to data-rich bird taxa. Here, we identify the optimum pretraining strategy for data-deficient domains using tropical reefs as a representative case study. We assembled ReefSet, an annotated library of 57k reef sounds taken across 16 datasets, though still modest in scale compared to annotated bird libraries at 2% of the sample count. We performed multiple pretraining experiments, finding that pretraining on a large library of bird audio provides notably superior generalizability on held out reef datasets with a mean AUC-ROC of 0.881 (±0.11) compared to pretraining on ReefSet itself or unrelated audio, with a mean AUC-ROC of 0.724 (±0.05) and 0.834 (±0.05) respectively. However, our key findings show that cross-domain mixing, where bird, reef and unrelated audio are combined during pretraining, provides a superior transfer learning performance, with an AUC-ROC of 0.933 (±0.02). SurfPerch, our optimum pretrained network, provides a strong foundation for automated analysis of tropical reef and related PAM data with minimal annotation and compute costs.