GetNetUPAM: New Framework for Reliable Marine Bioacoustic Monitoring in Noisy Conditions
Researchers have introduced GetNetUPAM, a hierarchical nested cross-validation framework paired with a noise-robust neural network architecture called ARPA-N, designed to improve the reliability of underwater passive acoustic monitoring (UPAM) of marine life. Current bioacoustic monitoring systems struggle with high-noise, low signal-to-noise ratio conditions and evaluation methods that inflate apparent performance, masking real-world failure modes. The work addresses a critical gap in scalable ecological monitoring by providing a reproducible benchmark that better reflects actual deployment conditions.
GetNetUPAM is a machine learning evaluation and modeling framework targeting underwater passive acoustic monitoring, a field used to track marine species through their vocalizations. The framework uses a nested cross-validation structure that partitions data into site-year blocks, preserving ecological heterogeneity and ensuring each evaluation fold represents a distinct environmental regime rather than allowing models to overfit to localized noise or sensor artifacts. Paired with this evaluation protocol is ARPA-N, a convolutional neural network that incorporates CBAM spatial attention to suppress noise and localize genuine biological call structures in spectrograms, avoiding spurious global cues exploited by standard CNNs. In tests on the zero-training-support Balleny Islands region — a location unseen during model development — ARPA-N reduced false positives per hour by approximately 10-fold at a fixed 90 percent recall rate, demonstrating strong generalization across diverse environmental regimes. The authors argue that conventional single-split evaluations obscure distribution shifts caused by variable sound propagation, mixed biological and anthropogenic noise sources, and sensor variability, leading to overly optimistic performance estimates. The paper has been resubmitted and is currently under review at IEEE Transactions on Artificial Intelligence, with final formatting pending. The work aims to move marine bioacoustic monitoring toward deployment-reliable, scalable ecological surveillance tools.
What's missing
The study is a preprint under peer review and has not yet been formally published; results have not been independently replicated. Key limitations not fully addressed include: the computational cost of nested cross-validation at scale, and whether the ~10x false positive reduction holds across a broader range of recall thresholds.
What different sources said
- arXiv cs.AICenter
GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.