6 papers
Physics-Informed Learning for Robust Acoustic Localization with Calibrated Uncertainty
Jennifer N. Kampe, Changwoo J. Lee, Xin Shen +5
Recent advances in Passive Acoustic Monitoring (PAM) offer an opportunity to obtain ecological spatial point-process data at unprecedented scale. However, realizing this opportunit…
ForestIR: Physics-Informed Forest Sound Simulation for Array-Based Bioacoustic Remote Sensing
Xin Shen, Jennifer N. Kampe, Changwoo J. Lee +7
Microphone array-based passive acoustic monitoring is increasingly used for biodiversity sensing in forests. However, design and evaluation of array systems and configurations rema…
Mixture-Constrained Max Pooling Improves Separation-Based Bird Species Classification
Yuzhu Wang, Kalle Lahtinen, Patrik Lauha +4
Bird species classification from field recordings remains challenging due to overlapping vocalizations and incomplete species labels. We study source separation as a preprocessing…
Scalable and robust regression models for continuous proportional data
Changwoo J. Lee, Benjamin K. Dahl, Otso Ovaskainen +1
Beta regression is used routinely for continuous proportional data, but it often encounters practical issues such as a lack of robustness to misspecification of the beta distributi…
Joint species distribution modeling of abundance data through latent variable barcodes
Braden Scherting, Otso Ovaskainen, David B. Dunson
Accelerating global biodiversity loss has highlighted the role of complex relationships and shared patterns among species in determining their responses to environmental changes. T…
OptimOTU: Taxonomically aware OTU clustering with optimized thresholds and a bioinformatics workflow for metabarcoding data
Brendan Furneaux, Sten Anslan, Panu Somervuo +4
To turn environmentally derived metabarcoding data into community matrices for ecological analysis, sequences must first be clustered into operational taxonomic units (OTUs). This…