top of page

IBCP co-authors new publication on how Artificial Intelligence (AI) can help prevent illegal wildlife trade

4 March, 2024

The Javan White-eye (Zosterops flavus) is one of many endangered species in the family Zosteropidae that is threatened by trapping for wildlife trade. Photo by FatihPR.


High demand for captive songbirds in east and southeast Asia is driving many species to the brink of extinction in the wild. Renowned for their beauty, white-eyes are very popular songbirds in Asian wildlife markets, and include many endangered species whose trade is prohibited by CITES. The ability to identify protected species is crucial for enforcing wildlife laws, but may be constrained by difficulties in distinguishing ‘look-alike’ bird species traded in markets. To address this challenge, we developed a novel deep learning-based Artificial Intelligence (AI) bioacoustic tool. We used three major avian vocalization databases to access bioacoustic data for 15 commonly traded, morphologically similar white-eye species. Specifically, we employed the Inception v3 pre-trained model to classify the 15 white-eye species and ambient sound (i.e. non-bird sound) using 448 recordings of white-eye vocalizations. We converted recordings into spectrograms and used image augmentation methods to enhance the performance of the AI neural network through training and validation. These techniques resulted in overall accuracy of up to 91.6% for identifying focal species. Our results are featured in a new publication that provides a foundation to enable citizen scientists and law enforcement officials to identify prohibited trade in threatened species efficiently and accurately, improving capacity for conservation law enforcement.


38 views0 comments


bottom of page