D. A. Coomes

Fire traps in the wet subtropics: new perspectives from Hong Kong

This study quantifies fire traps in wet subtropical Hong Kong, showing grasslands and shrublands are more fire-prone and recover slower than forests, with implications for restoration strategies.

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.

Logging alters tropical forest structure, while conversion to agriculture reduces biodiversity and functioning

The paper analyzes the impacts of logging and conversion to oil palm on tropical forest structure, biodiversity, and functioning in Borneo, finding that logging affects structure more than biodiversity, while conversion has greater impacts on biodiversity and functioning.

Tree segmentation in airborne laser scanning data is only accurate for canopy trees

This study benchmarks tree segmentation algorithms using a new benchmark dataset, finding high accuracy for canopy trees but low accuracy for understory trees.

Accurate delineation of individual tree crowns in tropical forests from aerial RGB imagery using Mask R-CNN

This paper introduces Detectree2, a deep learning model that accurately segments individual tree crowns in tropical forests from aerial RGB imagery, enabling growth and mortality analysis of large trees.