NJIT biologist among $10M XPRIZE competition winners for rainforest biodiversity sampling tech

NJIT's Eric Fortune and team “Limelight Rainforest” are grand prize winners of the global XPRIZE Rainforest Competition with their drone-delivered Limelight device, capable of identifying thousands of rainforest species in mere hours.

New Jersey Institute of Technology

 

image: 

Limelight uses telemetry, satellite communications and advanced AI to interpret the hundreds of thousands of images, recordings and samples collected by the platform’s advanced microphones, cameras and capture systems.

view more 

Credit: Limelight Rainforest

NJIT biologist Eric Fortune and a team of scientists called “Limelight Rainforest” have won the five-year XPRIZE Rainforest Competition, securing half of the competition's $10 million prize purse. 

The team's dramatic victory was announced Nov. 15 at the G20 Social Summit in Rio de Janeiro, the culmination of a global competition that began in 2019 when the nonprofit XPRIZE Foundation challenged innovators around the world to “develop technology to capture the true biological diversity of rainforests…and show the value of protecting the natural resources within them.”

Ultimately, Limelight Rainforest and its biodiversity sampling technology, “Limelight”, outshined the competition — topping an initial field of 300 teams from 70 countries, including six finalists that competed in Amazonas in Manaus, Brazil this past July.

“It's amazing. Being part of this crazy adventure over three years has been an enormous learning experience with so many twists and turns. It’s something I'll never forget," said Fortune, a team leader who developed sensor and control systems used in the Limelight data collection platform.

"The real reward is that this work can have a lasting impact on these vital ecosystems and the communities that depend on them. It’s what drew us to this competition in the first place.”

Originally started by Colorado Mesa University biology professor Thomas Walla, Limelight Rainforest forged its drone-based sampling technology under the unique rules of the competition's various stages held in rainforests around the world — teams have been challenged to deploy technologies to remotely survey as much biodiversity as possible across 100 hectares of forest accurately, and in under 24 hours.

VIDEO: XPRIZE Rainforest Finals Competition

The Limelight team of more than 50 engineers, biologists and indigenous scientists developed their system to collect a flurry of data on species that included ultrasound produced by bats and traces of DNA left by primates moving through the forest.

The latest Limelight uses telemetry, satellite communications and advanced AI to interpret the hundreds of thousands of images, recordings and samples collected by the platform’s advanced microphones, cameras and capture systems. The 24-hour sampling period was followed by a 48-hour sprint to produce a final report of species, their movements and deep insights into the forest's biodiversity.

Uncovering Life in the Amazon

On the heels of the semifinals hosted in Singapore, the XPRIZE Rainforest Competition finals were fittingly held in the Amazon — the most biodiverse place on Earth, estimated to be home to over 10% of the known species in the world.

“We were taken by boat to this remote location on the shores of the Rio Negro where they had a hut for us to spend the next 24 hours,” Fortune said. “Our team has a lot of experience in the Amazon, so we were confident, but we didn’t expect it to go so smoothly.

“We sent out 10 Limelight rafts with our drones once they put us on the clock, and from there everything just worked.”

Upon deployment, the team's devices — each equipped with five light trap cameras — lured and imaged an astonishing 250,000 insects that were classified in mere hours.

The Limelight’s new water sampling tool, deployed using custom robotic systems, filtered 45 liters of water from remote streams in narrow canopy gaps to catalog the vast biodiversity of the forest’s aquatic ecosystem. It yielded over 27 million environmental DNA (eDNA) sequencing reads on location.

The team also pioneered a new “Nature Node” acoustic system, capable of identifying bird and other tree-dwelling species by their vocalizations with unprecedented precision.

“For 40 years, people have been trying to track animals based solely on their vocalizations. It was a dream of mine as a grad student and our team made it happen,” Fortune noted.

VIDEO: Finals Testing Insect Timelapse

AI Trained by Indigenous Experts

One of Limelight’s biggest standout features in the finals was the accuracy of their AI in identifying the vast array of forest life.

For that, the team turned to the Quechua and Waorani Indigenous groups native to the rainforests of Ecuador, who reviewed and validated thousands upon thousands of sounds and images of rainforest species. Part of this effort was funded by a Kickstarter campaign to train their AI’s species identification capabilities.

“Many of our team members have been conducting research in Ecuador and building relationships with the Quechua and Waorani groups for over 20 years,” said Fortune. "Our Indigenous team members are the true masters of this knowledge. They were vital in helping confirm the identifications of these species … in many ways the team was completely reliant on their expertise.

“We were certain our AI was trained well because we had the world's top experts validating the data that we fed into the AI.”

Upon its XPRIZE success, the team is already planning to scale up Limelight production. Fortune is helping lead development of the first generation of Limelight devices for real-world use, partnering with NGOs, Indigenous communities and other organizations invested in rainforest conservation.

The experience is one he will not soon forget, but Fortune says the team’s work toward rainforest conservation has only just begun.

 “We're already identifying projects in South America and Southeast Asia where we could have an impact, redesigning our systems for these real-world needs,” said Fortune. “Once these devices start to be deployed, we will make enormous discoveries and uncover so many hidden organisms unique to these rainforests. It could change how we value and protect them.”

forest forged its drone-based sampling technology under the unique rules of the competition's various stages held in rainforests around the world — teams have been challenged to deploy technologies to remotely survey as much biodiversity as possible across 100 hectares of forest accurately, and in under 24 hours.

Credit

Limelight Rainforest

Florida Museum curator helps team score 1st-place and $5 million in international biodiversity competition

Florida Museum of Natural History

 

image: 

A team of scientists, robotics engineers and naturalists has won first place and $5 million in an international biodiversity competition.

view more 

Credit: Cat Kutz

Robert Guralnick, curator of bioinformatics at the Florida Museum of Natural History, is a member of an international team that won first place in the five-year XPRIZE Rainforest competition. The winners were announced Friday, Nov. 15 at a summit held in Rio de Janeiro. More than $7 million was awarded to the top-ranked teams, with $5 million going to the first-place winner.

XPRIZE is a non-profit, solutions-driven organization that has hosted large-scale competitions to solve humanity’s greatest challenges since it was established in 1994. The XPRIZE Rainforest competition kicked off in 2019, hosting 300 teams across 70 countries. The collective goal of each participant was the acceleration of technological innovation to improve the speed and precision of biodiversity surveys in support of global conservation efforts.

In the final stage of the competition, six finalist teams had 24 hours to deploy their technologies, remotely survey a 100-hectare test plot of tropical rainforest without physically entering the test area, and produce a biodiversity analysis report within 48 hours following the deployment. To win the competition’s grand prize, teams were also tasked with demonstrating scalability to effectively disrupt the often lengthy, laborious and resource-intensive process of data collection and analysis.

“It was such a massive collaborative effort,” Guralnick said. “I have never been involved in such a high-pressure situation, where one team does so much work to produce high-quality data, analytics and insights.”

Guralnick is a member of the Limelight Rainforest team, whose solution to the challenge was to create a monitoring device equipped with lights, audio recorders, cameras, insect traps and collection reservoirs. During the competition, each of ten Limelight devices was transported by drone and deposited in the forest canopy. At sundown, the lights were activated, creating clear beacons that attracted insects within the 100-hectare plot.

This strategy got them through the semifinals hosted last year in Singapore. The team made several tweaks and improvements to the collection apparatus ahead of the finals competition that took place in Amazonas, Brazil this April. The alterations enabled them to create an even more detailed snapshot of the world’s most biodiverse ecosystem.

Team members were brought on at various stages of the competition. Florida Museum researchers Raphael LaFrance and Nick Gardner also joined the Rainforest Limelight ranks, as did former University of Florida Ph.D. student Caitlin Campbell. Niyomi House, a postdoctoral associate at the Florida Museum, and Julie Allen, former Florida Museum Ph.D. student and current professor of biology at Virginia Tech, played equally indispensable roles.

During finals, the onboard camera systems photographed and automatically classified 250,000 insects in just 24 hours. Team members also used canopy mapping software to identify thousands of trees and piloted drones to collect water samples from the forest floor. Because organisms are constantly shedding genetic material into their environment, team members running an onsite genetic lab were able to sequence isolated strands of DNA suspended in the water samples and use it to identify many of the organisms that lived nearby.

The team used the Limelights’ audio recorders to automatically identify birds, using a birdsong database created in partnership with Indigenous bird guides in Ecuador.

Though the express goal was to measure as much biodiversity as possible, Guralnick said devices like the Limelight and others developed for the rainforest competition have the potential to go far beyond static inventories.

“One of the questions we want to answer is not so much what’s out there, but what services the forest is providing to animals,” he said. “For example, we can detect buzz feeding of bats in and around the site, which is an indication that it’s a high-quality area.”

By mapping the position of each monitoring device, the team could also triangulate the movement of birds and track bats as they searched for food.

The rainforest competition was developed to address the critical need for rapid biodiversity inventories in areas that remain poorly studied or are threatened by development. Devices like the Limelight will improve the accuracy of environmental assessments, make it easier to identify the ecosystem services provided within a plot of land and monitor ecosystem health in even the most remote areas.

“Our ability to deploy monitoring devices to explore the world is just in its infancy,” Guralnick said. “We’ve never before had the ability to get this type of dense, real-time, on-the-ground information on what’s happening in our ecosystems at this scale. When it comes to automated monitoring, we're learning to walk after crawling for a decade. I wonder what's going to happen when we can run.”

Visit the Limelight Rainforest’s website to learn more about the team and the technologies they’ve developed.