Ethan P. White

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 Portal Project archives over 40 years of continuous monthly rodent, biannual plant, multi-decade ant, and automated weather data from 24 experimentally manipulated Chihuahuan Desert plots with automated quality control.

This study develops an automated remote sensing approach to track individual bird nests using time-series UAS imagery in the Everglades, showing comparable performance to human assessment.

This paper presents an end-to-end workflow for near real-time monitoring of wading birds using drones and computer vision, achieving species-level counts for five out of six target species.

This study evaluates how ecological forecasting models perform under novel biotic conditions using a long-term desert rodent experiment, showing reduced accuracy and increased uncertainty when models are transferred to new conditions.

The paper uses computer vision and deep neural networks to predict individual tree species, crown characteristics, and locations across 24 sites in the National Ecological Observatory Network.

The paper develops a data workflow for managing evolving data in a long-term ecological study using version control and continuous integration tools.