How AI helps gather remote biodiversity data: Interview with Microsoft’s Juan Lavista Ferres

Two years ago, Microsoft's AI for Good Lab director Juan Lavista Ferres had an epiphany during a meeting with conservationists. The AI expert, who also serves as Microsoft's chief data scientist, realized a significant barrier in data collection for biodiversity studies. "It takes a huge amount of effort to collect data," Lavista Ferres told Mongabay in a video interview. "We never realized how bad it was until we worked closely with them [the conservationists] to see the whole workflow."

In response to this revelation, Ferres assembled a team to develop a solution. The result was Project SPARROW, an innovative system that harnesses the power of AI and edge computing to monitor biodiversity in real-time, continuously. The system is solar-powered and designed to operate autonomously in remote forests, gathering and processing both visual and audio data.

The main objective behind SPARROW is to simplify data collection for conservationists. "The whole idea of SPARROW is to make it trivial for conservationists to be able to collect data," Ferres explained. The system has been deployed in 11 countries across five continents and has proven that it can function continuously without human intervention for over a year. However, deploying SPARROW in remote forests presents its own set of challenges, as accessing the devices is difficult.

One such site is the Los Amigos biological station in Peru, operated by the Amazon Conservation Association. Despite the challenges, SPARROW's continuous operation in remote locations demonstrates its potential to revolutionize biodiversity data collection.