Soundscapes to Landscapes: Monitoring Animal Biodiversity from Space with the Help of Citizen Scientists



​Sonoma State University Professor Matthew Clark leads a NASA-funded project to monitor bird diversity, with the help of collaborative researchers, students and volunteers known as “citizen scientists.” The project, known as Soundscapes to Landscapes (S2L), relies on remote sensing, an important tool for long-term monitoring of biodiversity. S2L combines bioacoustic data collected by citizen scientists with satellite and environmental data to monitor bird diversity in Sonoma County, California.

S2L is using sound recordings collected by citizen scientists to map bird diversity across the region. The volunteers place low-cost, portable sound recorders, called AudioMoths, in various habitats in the county. The teams return to retrieve the recorders after two to five days and upload the “soundscape” recordings to a cloud-based bioacoustics platform called ARBIMON. Through a series of “bird blitzes,” citizen scientists use a custom interface on ARBIMON to validate example birdcalls in a subset of the recordings. These validation data are then used to train a “deep learning” computer algorithm to identify bird species present in all field-site recordings. 

The science team uses statistical modeling and satellite data to make maps of bird diversity based on the recordings collected by the citizen scientists. These maps are combined with habitat models based on two of NASA’s cutting-edge sensors: Global Ecosystem Dynamics Investigation (GEDI), a space-based lidar on the International Space Station, and a future satellite imaging spectrometer, called the Surface Biology and Geology mission, currently simulated from NASA’s airborne visible/ infrared imaging spectrometer (AVIRIS). Data collected from these sensors are used to understand species distribution and factors related to conserving bird diversity.

In the spring of 2019, the field campaign focused on surveying publicly owned properties with new research permits for Sonoma County Regional Parks, U.S. Fish and Wildlife Service and California State Parks. The project also obtained access to several larger private properties in the western area of Sonoma County and a large block of forest in the remote northwestern area of the county. Other volunteers participated through a “mail deploy” approach, in which landowners received AudioMoth recorders and instructions through the mail to deploy the unit on their property. Thirty-two citizen scientists participated in this activity. Collectively, volunteers spent 1,163 hours in the field. 

Citizen scientists also helped identify, tag and validate birdcalls in recordings in organized “bird blitzes” or at home. These birdcalls will be used to sort through soundscape recordings and accurately identify target bird species at survey sites. As part of this process, collaborators at University of California, Merced (UCM) developed a prototype deep learning framework to identify bird species in noisy audio recordings. Because the field audio data were still being acquired and birdcalls validated for training, team member Shrishail Baligar at UCM downloaded a large dataset of birdcall audio files from the xeno-canto website to train and evaluate the prototype deep learning methods. The initial results were promising.

The in situ bird diversity data from field sites, as measured by bioacoustics, will be used with remote sensing, climate and other predictor variables in species distribution models (SDM) that estimate the probability of occupancy for a given bird species. During year one, collaborative researchers greatly improved the SDM code from the prototype phase to perform multiple machine learning models on a High-Performance Cluster (HPC) at Northern Arizona University. In an SDM analysis with simulated GEDI and existing bird diversity data (from online database eBird and the North American Breeding Bird Survey), the team found that canopy structure, as measured by GEDI, was the second-most important group of predictor variables, after climate predictors. Canopy structure was particularly important in predicting the occupancy of conifer forest birds.

​ The Soundscapes to Landscapes project is a partnership of the Center for Interdisciplinary Geospatial Analysis (CIGA) at Sonoma State, Point Blue Conservation Science, Audubon California, Pepperwood Preserve, Sonoma County Agricultural Preservation and Open Space District, Northern Arizona University, UC Merced and University of Edinburgh.