Masanori Onishi

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.

The paper examines how crown-based growth strategies influence tree functional group distribution and co-occurrence across environmental gradients.

The paper introduces the Global Canopy Atlas, a harmonized dataset of 3D canopy structure from ALS data, and demonstrates its applications in validating satellite maps, analyzing canopy gap patterns, and quantifying forest turnover.