E. P. White

Individual tree crown maps for the National Ecological Observatory Network

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.

Restoring adiponectin via rosiglitazone ameliorates tissue wasting in mice with lung cancer.

This study shows that rosiglitazone restores adiponectin levels and preserves tissue mass in mice with lung cancer by enhancing AMPK and AKT activity.

Ketogenic diet promotes tumor ferroptosis but induces relative corticosterone deficiency that accelerates cachexia

This study shows that a ketogenic diet slows tumor growth but accelerates cachexia and shortens survival in IL-6-driven cancer models by inducing ferroptosis and corticosterone deficiency.

Continental-scale hyperspectral tree species classification in the United States National Ecological Observatory Network

The paper develops a continental-scale tree species classifier using NEON data, showing better accuracy than site-specific models and highlighting challenges in species classification across diverse ecosystems.

Data science competition for cross-site delineation and classification of individual trees from airborne remote sensing data

This paper runs a data science competition to improve methods for delineating and classifying individual trees from remote sensing data across multiple sites.

A general deep learning model for bird detection in high resolution airborne imagery

The paper develops a general deep learning model for bird detection in aerial imagery, achieving high recall and precision with minimal local training.

Disentangling the roles of inter and intraspecific variation on leaf trait distributions across the eastern United States

The paper develops a joint model to analyze how inter- and intraspecific variation influence leaf trait distributions across the eastern US, finding that intraspecific variation significantly contributes to trait variation.

A benchmark dataset for individual tree crown delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network

The paper introduces a benchmark dataset for evaluating individual tree crown delineation algorithms using co-registered remote sensing data and provides an R package for standardized evaluation.

Influence of climate forecasts, data assimilation, and uncertainty propagation on the performance of near-term phenology forecasts

This study evaluates a near-term phenology forecast system, finding that temperature data assimilation improves skill while climate forecasts contribute little overall.

A simulation study of the use of temporal occupancy for identifying core and transient species

This study simulates how temporal occupancy affects classification of core and transient species, finding that detection rates and habitat heterogeneity influence error rates.

Automated data-intensive forecasting of plant phenology throughout the United States

The paper develops an automated system for forecasting plant phenology across the U.S., predicting events like budburst and fall colors for 78 species up to 6 months in advance.

Geographic Generalization in Airborne RGB Deep Learning Tree Detection

This paper evaluates the generalization of RGB deep learning tree detection models across different forest types using data from the National Ecological Observatory Network, finding that a universal model performs as well as site-specific models.

Hotspot prioritizations show sensitivity to data type

The paper compares hotspot prioritizations using range maps and survey data, finding significant differences in species richness hotspots but more overlap for rare species.

Developing an automated iterative near-term forecasting system for an ecological study

This paper develops an automated iterative forecasting system for ecological systems, demonstrating its application to rodent abundance forecasts using monthly data from the Portal Project.

Comparison of large-scale citizen science data and long-term study data for phenology modeling

This paper compares phenology models built from citizen science data and long-term ecological study data, finding that model performance depends on dataset scale and complexity.

Forecasting biodiversity in breeding birds using best practices

This study evaluates biodiversity forecasts for breeding birds using best practices, finding that no model consistently outperformed a baseline constant richness model.

An extensive comparison of species-abundance distribution models.

The paper compares four species-abundance distribution models using likelihood and AIC across 16,000 communities, finding the log-series model provides the best fit overall.