S. S. Sethi

Unlocking the soundscape of coral reefs with artificial intelligence: pretrained networks and unsupervised learning win out

This paper demonstrates that pretrained neural networks and unsupervised learning effectively analyze coral reef soundscapes for ecological insights without manual annotation.

MAARU: Multichannel Acoustic Autonomous Recording Unit for spatial ecosystem monitoring.

The paper introduces MAARU, a low-cost, open-source multichannel acoustic recorder for spatial ecosystem monitoring, demonstrating its accuracy in localizing sounds and improving species identification.

Automatic vocalisation detection delivers reliable, multi-faceted, and global avian biodiversity monitoring

The paper applies a pre-trained bird vocalisation detection model to global audio datasets, achieving high precision for many species and enabling biodiversity monitoring across multiple spatial and temporal scales.

Snowmobile noise alters bird vocalization patterns during winter and pre-breeding season

This study uses deep learning to analyze acoustic data and shows snowmobile noise reduces bird vocalizations in winter and pre-breeding seasons, with some recovery after noise events.

Exploring the Spatiotemporal Influence of Climate on American Avian Migration with Random Forests

This study uses random forests to predict bird migration patterns based on climate data and eBird surveys, finding that lagged climate features improve predictions in October.

Is there an accurate and generalisable way to use soundscapes to monitor biodiversity?

This study investigates the generalisability of soundscape analysis for biodiversity monitoring and finds that acoustic features and machine learning models are inconsistent across datasets.

Soundscapes predict species occurrence in tropical forests

This paper shows that soundscapes can predict species occurrence in tropical forests without needing extensive labeled data, achieving high accuracy for many species.

SAFE Acoustics: an open-source, real-time eco-acoustic monitoring network in the tropical rainforests of Borneo

The paper presents an open-source, real-time eco-acoustic monitoring network in Borneo's tropical rainforests, providing code, design, and infrastructure for data collection and analysis.

Combining machine learning and a universal acoustic feature-set yields efficient automated monitoring of ecosystems

This paper develops a machine learning method using eco-acoustic data to monitor ecosystem changes and detect anomalies efficiently.

Robust, real-time and autonomous monitoring of ecosystems with an open, low-cost, networked device

The paper introduces an open-source, low-cost ecosystem monitoring system that autonomously captures and transmits continuous data, outperforming existing technologies at a fraction of the cost.

CCL3 promotes germinal center B cells sampling by follicular regulatory T cells.

The paper shows CCL3 promotes B cell interactions with follicular regulatory T cells in germinal centers, enhancing their negative regulation.