Research

Research Interests

I study mechanisms that generate, maintain, and preserve biodiversity.

The ecology of species interactions
Hierarchical Bayesian models for ecological predictions
Computer vision and machine learning for biodiversity image analysis

Deep Learning for Biodiversity Detection

I recently joined the weecology lab at the University of Florida to work on pioneering research for deep learning for biodiversity detection in remotely sensed imagery. Our first project focuses on combining LIDAR, hyperspectral and rgb data for tree segmentation and classification.

Demo: http://tree.westus.cloudapp.azure.com/trees/

Animal movement in dynamic landscapes

Using new satellite tracking technology, we are studying optimal foraging and the ecological predictors of animal movement.

Check out my interactive tools to visualize humpback whale movement and migration.

Identifying overlap between humpback whale foraging grounds and the Antarctic krill fishery. Weinstein, B. G., Double, M, Gales, N., Johnston D.W., and Friedlaender, A. S. 2017. Biological Conservation. 210: 184-191.

Weinstein, Ben G., and Ari S. Friedlaender. "Dynamic foraging of a top predator in a seasonal polar marine environment." Oecologia (2017): 1-9.

Specialization and Niche Overlap in Andean Hummingbirds

I study co-evolution and niche partitioning of tropical plants and hummingbirds in montane cloud forests.

Maquipucuna Ecolodge

Santa Lucia Ecolodge

Weinstein, B. G. and Graham, C. H. (2017), Persistent bill and corolla matching despite shifting temporal resources in tropical hummingbird-plant interactions. Ecol Lett, 20: 326–335. doi:10.1111/ele.12730

Live Data Dashboard: https://weinstein.shinyapps.io/HummingbirdData/

Co-occurrence and relatedness in ecological assemblages

Graham LJ, Weinstein BG, Supp SR, Graham CH. Future geographic patterns of novel and disappearing assemblages across three dimensions of diversity: A case study with Ecuadorian hummingbirds. Divers. Distrib. 2017;00:1–11. https://doi.org/10.1111/ddi.12587

Lessard, J.P., Weinstein, B.G., Borregaard, M.K., Marske, K.A., Martin, D.R., McGuire, J.A., Parra, J.L., Rahbek, C. and Graham, C.H., 2015. Process-Based Species Pools Reveal the Hidden Signature of Biotic Interactions Amid the Influence of Temperature Filtering. The American Naturalist, 187:75-88.

Penone, C.*, Weinstein, B. G.*, Graham, C. H., Hedges, S. B., Rondonini, C., Davidson, A. and C. G. Costa. 2016. Global mammal betadiversity reveals convergence between isolated forest assemblages. Proceeding of the Royal Academy B: Biological Sciences. 283: 20161028.
* authors contributed equally

Hierarchical Bayesian Models for Species Interactions

Bayesian N-mixture modeling for estimating detectability and traits from ecological network data.

Weinstein, Ben G., and Catherine H. Graham. "On comparing traits and abundance for predicting species interactions with imperfect detection." Food Webs (2017).

Source Code

Selectivity and Competitive Dominance

Do changes resources or the presence of competitors better explain species diet selectivity?

Weinstein, B. G. and Graham, C. H. 2016, Evaluating broad scale patterns among related species using resource experiments in tropical hummingbirds. Ecology, 97: 2085-2093.

Harnessing Computer Vision for Ecological Monitoring

The cost, time, and logistics of human observation limit many studies, yet ecologists have only begun to use automated tools. Computer vision is a field of computer science that extracts information from images and combines data taken from the field with automated image analysis.

Weinstein, B.G. (2015) MotionMeerkat: integrating motion video detection and ecological monitoring Methods in Ecology and Evolution, 6, 357–362.

Cruzan, M.B, Weinstein, B. G., Grasty, M. R., Kohrn, B., Schroyer, T and Pamela G. Thompson. 2016. Small Unmanned Aerial Vehicles (Micro-UAVs -Drones) in Plant Ecology. Applications in Plant Sciences. 4: 1600041.

Merging phylogeny and morphology with community ecology

Unraveling the evolutionary processes that lead to diverse assemblages.

Weinstein, B.G., Tinoco, B., Parra, J.L., Brown, L.M., McGuire, J. a., Stiles, F.G. & Graham, C.H. (2014) Taxonomic, Phylogenetic, and Trait Beta Diversity in South American Hummingbirds. The American Naturalist, 184, 211–224.

Past Research

Predicting Latent Risk for Global Mammal Diversity

A collaboration with Dr. Ana Davidson and NatureServe studying the morphological correlates of risk in global mammal diversity. Combining phylogenetic and functional trait data with machine learning models to identify the life-history and spatial characteristics of mammalian biodiversity risk.

Davidson, A. D., Shoemaker, K. T., Weinstein, B. G., Costa, G. C., Brooks, T. M., Ceballos, G., Radeloff, V. C., Rondinini, C. and C. H. Graham. Geography of current and future global mammal extinction risk. PlosONE. Accepted.

Biocultural Diversity in The Amazon Borderlands

Political Boundaries have a huge impact on both conservation and land use policy. Dr. David Salisbury (University of Richmond) and investigated whether the Amazonian Borderlands Region harbors greater biocultural richness as measured by avian and language diversity. We also look at the change in area protected as distance to a political border decreases (left):

Cultural Diversity in the Amazon Borderlands: Implications for Conservation and Development. David S. Salisbury, Ben G. Weinstein Journal of Borderlands Studies Vol. 29, Iss. 2, 2014

Methods in Landscape Genetics and Phylobetadiversity

Using a mechanistic energy budget (Gifford and Kozak 2012) of Red-cheeked Salamanders (left), i'm using least cost path approaches to explain population genetic differentiation.This research is in conjunction with Amy Luxbacher at the University of Minnesota as part of her doctoral work.