Julian Frey

The paper introduces MillionTrees, a global benchmark dataset for airborne tree detection, showing that current models struggle to generalize across diverse data and that training on MillionTrees improves performance.

AngleCam V2 estimates leaf inclination angles from daytime and nighttime photos across species, showing improved accuracy and generalization compared to its predecessor.

The paper predicts spatio-temporal patterns of soil respiration in a mixed forest using downscaled meteorological data, finding they outperform local parameters in explaining variability.

The paper introduces deadtrees.earth, an open-access database of high-resolution aerial imagery to map global tree mortality using community-sourced data and machine learning.

This study investigates how people perceive visual and acoustic diversity in forests and finds that acoustic perceptions are more strongly linked to actual species richness than visual ones.