Wed September 11, 2013
Dr. Mitchell Aide, University of Puerto Rico - Bugging Tropical Forests
In today’s Academic Minute, Dr. Mitchell Aide of the University of Puerto Rico explains how electronically bugging a tropical forest can provide insight about the native species.
Mitchell Aide is an associate professor of biology at the University of Puerto Rico where his research interests include tropical plant ecology biogeography, plant/herbivore interactions, and population genetics. His recent projects have focused on tropical ecology in Puerto Rico and Costa Rica. He holds a Ph.D. from the University Utah.
Dr. Mitchell Aide - Bugging Tropical Forests
To understand the impacts of deforestation and climate change, we need reliable long-term data on the fauna from around the world. Traditional sampling methodology, sending biologists to the field, is expensive and often results in incomplete and limited data sets because it is impossible to maintain biologists in the field 24 hours a day throughout the year.
To address this challenge our group of computer scientists and biologists have developed a system that will makes it much easier to monitor biodiversity. We do this by listening to the sounds of the forest.
With funding from the National Science Foundation we developed hardware and software to collect, process, and analyze audio recording in real-time. The hardware, which uses off-the-shelve components such as iPods and car batteries, records 144 one-minute recordings per day in remote sites and sends them in real-time to a base station up to 40 km away. The recordings are then forwarded to the project server in Puerto Rico where they are processed and made available to the world through the internet in less than a minute.
We tested the system with monitoring stations in Puerto Rico and Costa Rica, and by automating the collection of recordings, we rapidly had thousands of recordings that would be impossible to analyze by hand. This is where the software comes in. The web application we developed provides users with tools to train the software to automate species identification, and it would well for birds, frogs, insects and monkeys. Once the biologist has developed a reliable model, the computer can process more than 100,000 recordings in less than an hour, providing information on species presence and absence.
Conserving and managing the biodiversity in the world is a major challenge for society, particularly in the tropics. We hope that the tools we have developed will allow researchers, students, managers, and the public to better understand how these threats are impacting species, so that we can make informed conservation and management decisions.