K. E. Jones

Repatterning of mammalian backbone regionalization in cetaceans

This study investigates vertebral regionalization in cetaceans, finding that their backbone is less regionalized in the precaudal segment but more so in the caudal segment, indicating a repatterning of the vertebral column.

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.

Biodiversity shows unique responses to land-use change across regional biomes

This study identifies regional biomes as a better scale than biomes or realms alone to capture variation in biodiversity responses to land-use change, with consistent negative effects in tropical forests.

Towards a General Approach for Bat Echolocation Detection and Classification

This paper introduces BatDetect2, a deep learning pipeline for detecting and classifying bat echolocation calls, showing improved performance across diverse regions and species.

Rodent trapping studies as an overlooked information source for understanding endemic and novel zoonotic spillover.

This paper synthesizes rodent trapping studies in West Africa to improve understanding of rodent species distribution and host-pathogen associations, identifying gaps in current datasets and highlighting sampling biases.

CityNet - Deep Learning Tools for Urban Ecoacoustic Assessment

CityNet uses deep learning to measure biotic and anthropogenic sounds in cities, outperforming existing methods and showing realistic patterns across urban areas.

Evaluating Bayesian spatial methods for modelling species distributions with clumped and restricted occurrence data

This paper evaluates Bayesian spatial methods for species distribution modeling, finding that spatially-explicit INLA outperforms non-spatial methods in handling clumped and restricted occurrence data.

Bat Detective - Deep Learning Tools for Bat Acoustic Signal Detection

This paper develops and evaluates open-source deep learning tools for detecting bat echolocation calls in noisy audio recordings, showing improved performance over existing methods.