Jump to content

Is it possible to save a rainforest by listening to it?

A tribe in the Brazilian state of Pará is exploring ways to use old cell phones and machine learning to fight deforestation.

Turn on your audio for the best experience.

The Amazon rainforest, in all its majesty, is a very loud place.

A howler monkey howls.

Rain falls under the canopy.

A bird marks its territory. A macaw, to be exact.

But another sound lingers underneath, signaling that something else is here in the Amazon.

A chainsaw.

The Amazon is the largest tropical rainforest in the world, home to a quarter of the world’s biodiversity.

Since 1970, 20% of the Amazon has been destroyed by deforestation.

The indigenous Tembé people live on 2,800 km² of rainforest in northern Brazil. Over 30% of their territory has been deforested by cattle ranching, fires, and illegal logging.

Chief Naldo Tembé
“The biggest mark in my life was at the age of 8, when I went to do the first inspection [of the forest]. Back then, we heard a lot about loggers taking wood from our area, and I was outraged by seeing people stealing wood, [so] we mobilized.”

– Chief Naldo Tembé

As a boy, Naldo Tembé sacrificed any semblance of a normal childhood for the sake of the rainforest. He organized small groups of kids to survey their territory for illegal loggers without his parents’ knowledge, as the task of monitoring armed loggers is dangerous for anyone, let alone a child. He made his dedication for preserving the forest known to anyone who would listen, and his people took notice. When he turned 15, he was named chief.

Chief Naldo
Chief Naldo Tembé
“To be chief is a very heavy task, because you start to live others’ lives, not yours. And that is very tough. Even today, having been chief for many years, I haven’t really got used to it.”

– Chief Naldo Tembé

For the Tembé, life and forest are forever intertwined. When illegal loggers destroy the forest for profit, they aren’t just tearing down trees but the culture and heritage of people who’ve lived there for centuries.

While Chief Naldo was fighting to preserve his people’s land, in a village across the territory, Dona Verônica Tembé was mounting a campaign to help the tribe reclaim their culture. She encouraged the Tembé people to hold traditional festivities and to speak their own language alongside Brazilian Portuguese. Today, her granddaughter Marcelina Kuda teaches the Tembé language to a new generation at the village school, hoping they will be the cultural stewards of the forest for a new generation.

Cuda Tembé teaching her students the native Tembé language in a classroom.

Over the past 30 years, Chief Naldo and the tribe have wrestled back substantial portions of their land from the invaders, but detecting new illegal logging activity has continued to be a dangerous endeavor. Illegal loggers enter the Tembé land under the cover of night and can decimate hundreds of acres of forest without being detected. The ever-present sounds of the rainforest drown out the noise from the loggers’ chainsaws and trucks, making monitoring thousands of square kilometers of rainforest a nearly impossible task.

The Tembé people are well organized, well educated; they are not afraid to use new tools and new technologies. They are looking for collaboration. They’re not looking for help.

– Topher White, founder of Rainforest Connection

In 2014, Chief Naldo reached out to Topher White, founder of environmental nonprofit Rainforest Connection, and together they embarked on an ambitious project using recycled Android phones and TensorFlow, Google’s open-source machine learning model, to track the sounds of illegal logging in real time.

How recycled cell phones and machine learning help the Tembé protect their homeland

Recycled mobile phones and machine learning.

An Android phone is affixed to a solar power adapter and external microphone. These devices, nicknamed Guardians, can hear the sounds of illegal logging up to 1 kilometer away.

An Android phone is affixed to a solar power adaptor and external microphone.

The Guardians are hidden high up in trees for better cell service and access to sunlight for power. They listen to all the sounds of the forest around the clock.

Technologically advanced dashboard helps in identifying different sounds in the forest to save trees.

Rainforest Connection’s TensorFlow model uses machine learning to analyze the audio recorded by the Guardians, and learns to identify the sounds of chainsaws and logging trucks.

Chief Naldo Tembé used old mobiles to save rainforests of his region.

Within minutes of an identification, a real-time alert is sent to the Tembé rangers, a select security force of villagers who can intervene or report the logging activity to the authorities.

Rainforest Connection is putting this same acoustic monitoring system into the hands of other partners fighting deforestation in five different countries, including Peru, Ecuador, and Romania.

Today, Chief Naldo and the tribe are canvassing their land, climbing trees to install and maintain the Guardian devices, and responding to the logging alerts they receive. Armed with this new technology, the Tembé have a chance to safeguard not only their forest but their entire way of life.

Chief Naldo Tembé
“This was my grandfather’s big dream, and then it became my parents’ big dream, and today it is the great dream of my life, trying to leave the best for my children and grandchildren. There are great expectations as to what can happen from now on.”

– Chief Naldo Tembé

Young members of the Tembé celebrating their culture by wearing face-paint and headdresses.

Watch how the Tembé and Rainforest Connection are working together to bring this ambitious plan to life in the film below.

Related Stories

How your smartphone could help save your life in an emergency

How your smartphone could help save your life in an emergency

How six young women are using technology to tackle unsafe drinking water

How six young women are using technology to tackle unsafe drinking water

Meet the team using machine learning to help save the world's bees

Meet the team using machine learning to help save the world's bees

A veteran finds a new mission to build a more inclusive world

A veteran finds a new mission to build a more inclusive world

How AI is helping provide advance warnings in emergency situations

How AI is helping provide advance warnings in emergency situations

How one city is leading in urban forestry to fight climate change

How one city is leading in urban forestry to fight climate change

How your smartphone could help save your life in an emergency

How your smartphone could help save your life in an emergency

How six young women are using technology to tackle unsafe drinking water

How six young women are using technology to tackle unsafe drinking water

Meet the team using machine learning to help save the world's bees

Meet the team using machine learning to help save the world's bees

A veteran finds a new mission to build a more inclusive world

A veteran finds a new mission to build a more inclusive world

How AI is helping provide advance warnings in emergency situations

How AI is helping provide advance warnings in emergency situations

How one city is leading in urban forestry to fight climate change

How one city is leading in urban forestry to fight climate change

How your smartphone could help save your life in an emergency

How your smartphone could help save your life in an emergency

How six young women are using technology to tackle unsafe drinking water

How six young women are using technology to tackle unsafe drinking water

Meet the team using machine learning to help save the world's bees

Meet the team using machine learning to help save the world's bees

A veteran finds a new mission to build a more inclusive world

A veteran finds a new mission to build a more inclusive world

How AI is helping provide advance warnings in emergency situations

How AI is helping provide advance warnings in emergency situations

How one city is leading in urban forestry to fight climate change

How one city is leading in urban forestry to fight climate change

Back to top