Google’s machine-learning tool is being used to detect and combat illegal deforestation

The news:  Rainforest Connection, a San Francisco nonprofit, has developed a cheap, rigorous acoustic monitoring system made from modified cell phones and solar panels. An app on the so-called Guardian devices, which can be hidden in trees throughout forests, continuously listens for the telltale signs of illegal logging and animal poaching.

On March 21, the organization announced that it will be using Google’s TensorFlow, a free tool that makes it simpler for other companies and groups to develop machine-learning software (see “Google stakes its future on a piece of software”). Rainforest Connection says it will enable the organization to more accurately detect troubling sounds in the uploaded audio, such as chainsaws, vehicles, and gunshots.

Why does it matter? Deforestation reduces biodiversity, increases erosion, and promotes desertification. Felled trees also release carbon dioxide back into the atmosphere, accounting for around 10 percent of global emissions driving climate change, according to an earlier NASA study. Between 50 percent and 90 percent of all logging in tropical countries is done illegally, according to a 2012  report by the UN and Interpol.

The final word: “When fighting deforestation, every improvement can mean one more saved tree,” Rainforest Connection said in a blog post.