UH Hilo bioacoustics lab co-hosts competition for birdsong coding, $10K prize money
Collaborating with groups such as the Cornell Lab of Ornithology and Google Bioacoustic Group, the UH Hilo LOHE Lab is co-hosting a public coding competition calling for birdsong classification models, focusing on endemic birds of Hawaiʻi.
By Susan Enright/UH Hilo Stories.
A laboratory at the University of Hawaiʻi at Hilo that specializes in the ecology and conservation of native Hawaiian forests and birds is co-sponsoring a competition to help develop song detection algorithms for Hawaiian birds.
“The goal is, through collaboration with Cornell Lab of Ornithology and Google, to improve our techniques for monitoring the distribution and abundance of our birds in Hawaiʻi,” says Pat Hart, professor of biology and founder of the Hart Lab also known as the Listening Observatory for Hawaiian Ecosystems (LOHE) Laboratory.
“Currently, we have the ability to place automated recorders in our forests to record the birds for long periods of time, but analyzing the recordings must be done manually and is incredibly slow,” Hart explains. “Through the development of song detection algorithms, we can automate this process and speed up the analysis process by orders of magnitude.”
Hart says the new competition on the platform Kaggle attracts the brightest computer coders from around the world to address the Hawaiian bird extinction crisis. Competitors develop a model that can process continuous audio data and then acoustically recognize the species. The best entries are able to train reliable classifiers with limited training data.
The BirdCLEF2022 competition project with a $10,000 prize is headed by Amanda Navine, who graduated last fall from the UH Hilo tropical conservation biology and environmental science graduate program. Navine now works as an acoustic bioinformatics specialist at the LOHE Lab to develop song detection algorithms for Hawaiian birds.
“I have been working on a project using machine learning to develop an automated bird song detection and classification software called BirdNET,” Navine says. “What a useful tool this could be for advancing endangered species monitoring and research efforts.”
BirdNET is a research platform that aims to recognize birds by sound at scale. It support various hardware and operating systems such as Arduino microcontrollers, the Raspberry Pi, smartphones, web browsers, workstation PCs, and cloud stations. The BirdNET research project uses artificial intelligence and neural networks to train computers to identify nearly 3,000 of the most common species of North America and Europe. Users record a file using the internal microphone of an iOS device to find out if BirdNET correctly identifies the probable bird species present in the user’s recording.
Navine has been collaborating with groups such as the Cornell Lab of Ornithology and Google Bioacoustic Group to host the public coding competition calling for birdsong classification models. The researchers are focusing on birds that are endemic to the chain of islands of Hawaiʻi.
“We hope to incorporate promising elements from submitted models to improve BirdNET,” she says.
“There has been significant progress in this area of research in recent years, but we are not there yet,” explain the developers on the BirdCLEF2022 website. “This is especially true for rare and endangered bird species. In many cases, only very few training recordings exists for those birds, yet, they’re significantly more important to monitor due to their elevated conservation status.”
The competition is an annual exercise to help collect data. The group has collected soundscape recordings and expert labels for 10 Hawaiian bird species, and Navine prepared a notebook that introduces each of the birds to competitors so they can see what is needed to compete.
The project is based on the concept of open sourcing, and participants must ensure the external data used is publicly available and equally accessible to use by all participants of the competition.
Story by Susan Enright, public information specialist for the Office of the Chancellor and editor of UH Hilo Stories. She received her bachelor of arts in English and certificate in women’s studies from UH Hilo.
