Artificial Intelligence and Rainforest Connection

Original article can be found here (source): Artificial Intelligence on Medium

Artificial Intelligence and Rainforest Connection

Using AI to Detect Immediate Threats from Illegal Logging and Track Rainforest Health

I was able to find out about the Rainforest Connection through an interview with a programme manager in Google named Brigitte Hoyer Gosselink. She had previously worked in international development and later joined Google. In an article in GreenBiz on the 11th of March 2020 she was interviewed and told about a company that I found interesting, namely: Rainforest Connection.

Rainforest Connection is a company that develops open-source software and systems to help preserve rainforests, is using AI and acoustic monitoring to detect immediate threats from illegal logging and track rainforest health.

In doing so they use TensorFlow, Google’s open-source machine learning framework, aids in their efforts. Interviewed in a recent blog post published by Google the CEO Topher White of Rainforest Connection shares his concerns. He argues that the activity to prevent and preserve is vitally important for our planet:

“…destruction of forests accounts for nearly one-fifth of all greenhouse gas emissions every year. And in the tropical rainforest deforestation accelerated on the heels of rampant logging — up to 90 percent of which is done illegally and under the radar.”

Rainforest Connection is a group of engineers and developers focused on building technology to help locals. They have helped the Tembé tribe from central Amazon — protect their land. With this they say that they have built the world’s first scalable, real-time detection and alert system for logging and environmental conservation in the rainforest. They can recycle old Android phones into solar powered devices that listens to sounds of illegal logging in an area.

Screenshot of Rainforest Connection website retrieved the 15th of March 2020

Once the audio is in the cloud, they use TensorFlow, Google’s machine learning framework, to analyse all the auditory data in real-time and listen for chainsaws, logging trucks and other sounds of illegal activity that can help us pinpoint problems in the forest.

In 2018 they launched the “Planet Guardians” program with hundreds of students from Los Angeles STEM science programs. This program involved speaking with local Tembé Tribe through Google Hangouts as well as building their own Guardian devices to be sent to the Amazon.

Looking at their website on the 15th of March 2020 they give examples of where they operate.

  • Alto Mayo, Peru. The biodiversity of Peru’s Alto Mayo rainforest is slowly being whittled away by systemic illegal logging, poaching, and drug trafficking. Working in conjunction with Conservation International (CI) and Peruvian government rangers, Rainforest Connection is testing an acoustic alert system that listens for telltale indicators of deforestation (chainsaws) or animal poaching (motorcycles) — as well as for trucks and vehicles that indicate narco-trafficking.
  • Cerro Blanco, Ecuador. One of Ecuador’s most diverse rainforest preserves, Cerro Blanco lies in close proximity to the sprawling metropolis of Guayaquil. As a result, it faces threats from deforestation, poaching, and urban encroachment. In concert with Fundacíon Pro Bosque (FPB), RFCx has set up a system to monitor for illegal chainsaws and poaching in real-time. In addition to helping better protect 10,000 hectares of rainforest, our system also streams 1.8 gigabytes of data per day, giving scientists and conservationists a means of keeping track of endangered wildlife. This project includes real-time alerts and data analysis for several species of rare parrots, assisting local rangers and biologists by helping them monitor endangered species and safeguard their habitat from poachers.
  • Tembé Tribal Reserve, Northern Brazil. Due to scarcity of numbers, the Tembé people of northern Brazil have found it difficult to put an end to large scale illegal logging, poaching, and drug smuggling operations in remote areas of their ancestral rainforests. Based on our 2015 pilot, the Tembe have asked RFCx to deploy a permanent system to help them protect the rainforest reserve — a monitoring system that can act as a force multiplier for a handful of trained Tembe Rangers. Our 2018/19 focus includes deploying and expanding this system to alert Tembé Rangers to indications of illegal logging (chainsaws), poaching (motorcycles), and smuggling (trucks/vehicles). Moreover, our system has already created a host of wifi hotspots in remote areas that has allowed the tribe to communicate more effectively among themselves — as well as with the outside world, erasing the digital divide.
  • Cameroon. Home to some of the world’s most richly dense rainforests, Cameroon is no stranger to illegal logging and poaching at an industrial scale. In partnership with the Zoological Society of London (ZSL) and a local sustainable logging company named Rougier, Rainforest Connection set up an acoustic monitoring to demonstrate our system could assist local park rangers in detecting unauthorized activities in protected areas that included the poaching of chimpanzees, gorillas, elephants and a host of other endangered birds.
  • Sumatra. Illegal deforestation continues to endanger the native habitat of Sumatra’s gibbons — even in designated nature preserves. Working in concert with the Kalaweit Supayang Gibbons Reserve, Rainforest Connection pioneered an acoustic monitoring system that could detect the sound of chainsaws in the cacophony of the jungle — and instantly alert park rangers to the source of the noise. Right from the start, the results were remarkable: For the first time ever, staff members on the Reserve found themselves able to confront illegal loggers live and in person — and shut down their operations.

As such Rainforest Connection is truly a company to keep an eye on if you are interested in climate change and artificial intelligence.

Their CEO spoke at TED so it may help to see his presentation: