Associate Professor David Luther, who has spent the last 14 years in George Mason’s Biology Department studying ecology, evolution, and conservation, recognizes the importance of playing the long game in research and education. Great outcomes don’t happen overnight. But even Luther couldn’t have imagined the hurdles and roadblocks ahead of him following 4-VA@Mason’s approval of his 2019 Collaborative Research Grant proposal “Species richness resilience to habitat fragmentation and restoration in tropical rainforests.”
Luther’s vision was to document and measure differences, using audio and video devices, in the animal community composition and the rate of recovery of animals in secondary forest and forest fragments – areas where contiguous forested areas are broken into smaller forest patches, separated by barriers such as roads, agriculture, or utility corridors. His plan was to install recording equipment at 50 sites as part of the Biological Dynamics of Forest Fragments Project (BDFFP) in the Amazon rainforest of Brazil. Luther paved the way for this project by connecting with the Brazilian National Institute of Amazonian Research (INPA), an Amazon research institution based in Manaus.
The proposed budget was entirely devoted to purchasing the wide array of materials necessary for the effort — cameras, acoustic recorders, batteries, and other supplies — along with the international travel needed to bring the project to fruition. Luther then assembled a team of faculty and student research volunteers at 4-VA partner schools and on the George Mason campus.
Just underway in 2019, all efforts came to a complete halt in March 2020 as Covid-19 struck worldwide. Luther faced a myriad of challenges: the inability to travel to Brazil and enter the field site; students selected for the research had to pivot to new endeavors which would allow them to graduate while studying remotely; and partner schools needed to move on to other projects during what would be the two-year waiting period. What’s more, one of the key members of the planning team, George Mason’s Tom Lovejoy, passed away in December of 2021. Lovejoy was recognized as one the world’s leading conservation biologists and often referred to as the “godfather of biodiversity.” In his passing, Luther lost a critical member of the team and a mentor.
However, Luther stayed the course, revamped his team, re-wrote the schedule, and maintained his commitment to get the project moving forward as soon as possible. Finally, in June 2022, he received the green light to move ahead. Between June and October 2022, 136 cameras and 81 acoustic devices were installed across 50 sites at BDFFP.
Today, to Luther’s great delight, the results have proved far more successful than he could have ever anticipated. Tens of thousands of animal images from camera traps and audio recordings have already been collected.
To analyze the data, Luther built a team of 15 George Mason undergraduate researchers, artificial intelligence experts, and a non-profit organization (Arbimon) that specializes in analyzing acoustic recordings from the tropics to help identify animals.
In the fall of 2022, Luther mentored student researchers to help with the endeavor. Aline Medeiros, a PhD student in Environmental Science and Policy (ESP), helped manage the undergraduate researchers working on the audio files. Volunteer students on this project were Alexis Lembke, Amanda Jones, Adriana Em, Madison Cheung, Morgan Ellingsworth, and Grace Carriero. Medeiros will also use the captured data as the basis of her PhD research.
Another set of students helped identify animals in the camera images and entered that information into a large database. Hibo Hassan, Jordan Seidmeyer, Katie Russell, Carolian Sanabria, Adrian Em, Alix Upchurch, Piper Robinson, Tristan Silva-Montoya, and Estefany Umana spent hours creating this treasure trove of records. Emilia Roberts, a MS student in ESP, managed these undergraduate researchers.
Explains Luther, “For the acoustic recordings, we built templates for 250 bird species, and trained AI models to automatically detect and classify songs for each. We have already detected 201 of the 250 species. The model performed very well in our evaluations, achieving an average precision across all classes of 0.94. Thanks to our model, new recordings can be passed through it to automatically detect species calls, facilitating long-term monitoring and efficient analyses moving forward. We are now working with local experts in Manaus, Brazil to apply the same platform for frogs at our study sites in the Amazon rainforest.”
The biodiversity data of birds and mammals is being used to assess how each species responds to variations in forest structure and recovery from forest fragmentation. Luther brought on Konrad Wessels from George Mason’s Geography & Geoinformation Science Department to assist with satellite information from the Global Ecosystem Dynamics Investigation instrument (GEDI). GEDI uses high resolution lasers to provide detail in three-dimensional forest structure. The GEDI results will build predictive models looking at how the three-dimensional forest structure can forecast mammal and bird diversity and individual species occurrence in tropical rainforests. In an important finding, the team has determined that the diversity of three-dimensional forest structure heights and density of foliage is the biggest predictor of mammal and bird diversity.
The project continues to gain traction. The team has created a website featuring the results of the acoustic portion of the research, https://bio.rfcx.org/bdffp-acoustics, which has been very well received.
In addition, some of the acoustic training models were used by teams competing for the X-Prize, a competition designed to encourage technological developments supporting “radical breakthroughs for the benefit of humanity.”
Luther also applied for and received a $200,000 National Science Foundation grant which built off of the 4-VA funded study and is being used in part to continue both the camera and acoustic research. Luther and Wessels recently submitted a grant to NASA to expand on the research findings and apply them to the entirety of the Amazon basin.
Concludes Luther, “Through 4-VA@Mason, this project is up, running, and delivering fantastic information that will help scientists worldwide better design monitoring schemes for biodiversity in remote tropical forests, as well as those interested the relationship between habitat structure and degradation and species resilience to disturbance. The grant helped us get to the first step, and we are confident this project will continue to expand in the future with our excellent Brazilian collaborators, current NSF funding, and other future external funding.”