Search for: All records

Remote sensing can provide continuous spatiotemporal information about vegetation to inform wildlife habitat estimates, but these methods are often limited in availability or lack adequate resolution to capture the three‐dimensional vegetative details critical for understanding habitat. The Global Ecosystem Dynamics Investigation (GEDI) is a spaceborne light detection and ranging system (LiDAR) that has revolutionized the availability of high‐quality three‐dimensional vegetation measurements of the Earth's temperate and tropical forests. To date, wildlife‐related applications of GEDI data or GEDI‐fusion products have been limited to estimate species habitat use, distribution, and diversity. Here, our goal was to expand the use of GEDI‐based applications to wildlife demography by evaluating if GEDI data fusions could aid in characterizing demographic parameters of wildlife. We leveraged a recently published dataset of GEDI‐fusion forest structures and capture–mark–recapture data to estimate the density and survival of two small mammal species, Humboldt's flying squirrel (Glaucomys oregonensis) and Townsend's chipmunk (Neotamias townsendii), from three studies in western Oregon spanning 2014–2021. We used capture histories in Huggins robust design models to estimate apparent annual survival and density as a derived parameter. We found strong support that both flying squirrel and chipmunk density were associated with GEDI‐fusion forest structures of foliage height diversity and plant area volume density in the 5–10 m strata for flying squirrels and proportionately higher plant area volume density in the 0–20 m strata for chipmunks, as well as other spatiotemporal factors such as elevation. We found weak support that apparent annual survival was associated with GEDI‐fusion forest structures for flying squirrels but not for chipmunks. We demonstrate further utility of these methods by creating spatially explicit density maps of both species that could aid management and conservation policies. Our work represents a novel application of GEDI data to evaluate wildlife demography and produce continuous spatially explicit density predictions for these species. We conclude that aspects of small mammal demography can be explained by forest structure as characterized via GEDI data fusions. 

Abstract The biodiversity crisis necessitates spatially extensive methods to monitor multiple taxonomic groups for evidence of change in response to evolving environmental conditions. Programs that combine passive acoustic monitoring and machine learning are increasingly used to meet this need. These methods require large, annotated datasets, which are time‐consuming and expensive to produce, creating potential barriers to adoption in data‐ and funding‐poor regions. Recently released pre‐trained avian acoustic classification models provide opportunities to reduce the need for manual labelling and accelerate the development of new acoustic classification algorithms through transfer learning. Transfer learning is a strategy for developing algorithms under data scarcity that uses pre‐trained models from related tasks to adapt to new tasks.Our primary objective was to develop a transfer learning strategy using the feature embeddings of a pre‐trained avian classification model to train custom acoustic classification models in data‐scarce contexts. We used three annotated avian acoustic datasets to test whether transfer learning and soundscape simulation‐based data augmentation could substantially reduce the annotated training data necessary to develop performant custom acoustic classifiers. We also conducted a sensitivity analysis for hyperparameter choice and model architecture. We then assessed the generalizability of our strategy to increasingly novel non‐avian classification tasks.With as few as two training examples per class, our soundscape simulation data augmentation approach consistently yielded new classifiers with improved performance relative to the pre‐trained classification model and transfer learning classifiers trained with other augmentation approaches. Performance increases were evident for three avian test datasets, including single‐class and multi‐label contexts. We observed that the relative performance among our data augmentation approaches varied for the avian datasets and nearly converged for one dataset when we included more training examples.We demonstrate an efficient approach to developing new acoustic classifiers leveraging open‐source sound repositories and pre‐trained networks to reduce manual labelling. With very few examples, our soundscape simulation approach to data augmentation yielded classifiers with performance equivalent to those trained with many more examples, showing it is possible to reduce manual labelling while still achieving high‐performance classifiers and, in turn, expanding the potential for passive acoustic monitoring to address rising biodiversity monitoring needs. 

The urgency for remote, reliable and scalable biodiversity monitoring amidst mounting human pressures on ecosystems has sparked worldwide interest in Passive Acoustic Monitoring (PAM), which can track life underwater and on land. However, we lack a unified methodology to report this sampling effort and a comprehensive overview of PAM coverage to gauge its potential as a global research and monitoring tool. To address this gap, we created the Worldwide Soundscapes project, a collaborative network and growing database comprising metadata from 416 datasets across all realms (terrestrial, marine, freshwater and subterranean).