arXiv Statistics ML By Jiaxiang Ji, Laura Nazzaro, Ahmed Aziz Ezzat

A Deep Zero-Inflated Model of North Atlantic Right Whale Presence To Support Blue Economy Management in the U.S. East Coast

Read the original on arXiv Statistics ML →

The paper introduces the Deep Zero-Inflated Bernoulli (DeepZIB) model, a deep statistical framework that jointly estimates latent North Atlantic Right Whale presence and detection probabilities from passive acoustic monitoring data. It addresses challenges such as zero inflation, imperfect detection, and complex habitat dependencies, and demonstrates improved predictive performance and model adequacy through simulations and real-world application along the U.S. East Coast. The model produces high-resolution, spatiotemporal presence maps that can inform targeted, risk-aware management of blue economy activities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

arXiv Machine Learning
Sep 15

Large-scale bioacoustic detection using semantic segmentation: a deep learning framework applied to fin whale calls in ocean-bottom seismometer recordings

arXiv:2609.13281v1 Announce Type: cross Abstract: Ocean-bottom seismometers (OBS), originally deployed for geophysical research, continuously record low-frequency sound for months to years across bro...

By Jocelyn Japnanto, Alex A. Saoulis, Miriam Romagosa, Rita Leit\~ao, Gabrielle Arrieta, M\'onica A. Silva, Matthew Graham, Ana M. G. Ferreira
arXiv Computer Vision
Sep 3

Efficient Passive Acoustic Monitoring of Killer Whales Using a Two-Stage Detection and Ecotype Classification Cascade

The paper presents a lightweight ResNet-based two-stage cascade for passive acoustic monitoring of killer whales. First, it detects vocalizations, then it classifies confident detections into five eastern North Pacific ecotypes, abstaining on ambiguous calls. The pipeline achieves high macro‑F1 scores on the DCLDE 2027 dataset and improves real‑time inference speed, while active learning adapts the detector to new acoustic environments.

By Daniela Ruiz, Manuel Castellote, Zhongqi Miao, Carl Chalmers, Bruno Demuro, Rahul Dodhia, Pablo Arbelaez, Juan M. Lavista
arXiv AI
Jun 12

GetNetUPAM: Ecologically Informed Nested Cross-Validation and Noise-Robust Attention for Marine Bioacoustic Monitoring

arXiv:2509. 04682v2 Announce Type: replace-cross Abstract: Deploying reliable bioacoustic monitoring systems requires models that generalize under high-noise, low-SNR conditions and evaluation protocols that expose deployment-relevant failure modes, gaps largely unaddressed in current UPAM practice.

By Nicholas R. Rasmussen, Rodrigue Rizk, Longwei Wang, KC Santosh
arXiv Computer Vision
Aug 24

WildFin: An In-the-Wild Dataset for Fish Behavioral Recognition

arXiv:2608.21281v1 Announce Type: new Abstract: Recent advances in field technology have led to a massive influx of in-the-wild video data for ecological science. The primary bottleneck in leveraging...

By Abigail G. Grassick, Jerome Tze-Hou Hsu, Ethan Lin, Ziang Liu, Max Whitton, Madelyn Hair, Liam Gutierrez, Haozheng Yu, Kristin Branson, Vivek Jayaraman, Michael A. Gil, Andrew M. Hein, Jennifer J. Sun