Bioacoustic monitoring with machine learning (ML) models can provide valuable insights for informed decision-making in conservation efforts. In this study, the team built deep convolutional neural networks to analyze field recordings and classify calls of regionally rare bird species. Limited training data is a challenge for model running on rare species. This study describes the use of transfer learning, data augmentation, and K-fold cross validation to improve species presence survey results.
For the DOI, click here.
To view the project website, click here.