New Technology Tracks Species by Their Sounds

A new cyber infrastructure developed by scientists enables real-time acoustic recording and automatic species identification in remote locations of the world, offering anyone in the world quick and easy access of not only what creatures inhabit a given area, but how many of them there are - a key to measuring nature's response to on-going climate change and human invasion.

Called the Automated Remote Biodiversity Monitoring Network (ARBIMON), the system includes solar powered stations that send one-minute recordings every 10 minutes to a base station where the recordings are processed and uploaded to a website. In addition to a module for viewing, listening and annotating recordings, the site includes a species identification interface to help users create machine learning algorithms to automate species identification.

Led by Mitchell Aide and Carlos Corrado-Bravo of the University of Puerto Rico, the hardware utilizes cheap and easily obtained components, such as iPods and car batteries. In doing so, the system offers easier, more extensive and far cheaper monitoring of species.

"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, and it is impossible to clone expert field biologists so that they can monitor various sites simultaneously," Aide explained in a press release.

As proof of the value of the system, the researchers published in the journal PeerJ analyses of a recently described species of endangered frog in Puerto Rico. Using ARBIMON, the scientists were able to demonstrate a significant decline in calling activity over the course of four years before a sudden spike back to original levels during the fifth. Though a common dynamic in many species, it nevertheless has often been difficult to measure - until now.

"Each recording is the equivalent of a museum sample, which can be analyzed with the knowledge and technologies we have today," Corrada-Bravo explained, "but which will be permanently stored so that biologists 20 or 50 years from now, will be able to analyze these recordings with new technologies and ideas."