Robert Anderson

2011 Regional Award Finalist — Faculty

Robert Anderson

Current Position:
Professor of Biology

Institution:
City College CUNY

Discipline:
Ecology

Recognized for: Applying an advanced approach from machine learning to a key problem in ecology and biogeography

Areas of Research Interest and Expertise: Biodiversity, biogeography, climate change, ecological modeling, mammals

"I aim to provide techniques that researchers can use to make realistic predictions of species current and future distributions, for application to environmental issues of importance to society.  In addition to conceptual and methodological advances, this requires automation of best practices allowing users to make high-quality and statistically defensible models."

Biography:

PhD, Biology, University of Kansas
BA, Biology, Kansas State University

Robert Anderson is known for his influential research in the field of ecological niche modeling of the geographic distribution of species. He started with a Fulbright fellowship to the Universidad de los Andes in Bogotá, Colombia. By the time he returned for his PhD at the University of Kansas in 1995, he appreciated first-hand the gaps in scientific knowledge about species and their natural history, even in better-characterized groups such as mammals. That realization seeded his interest in computer modeling, a process with the potential to fill these gaps.

After he arrived in New York in 2001, Dr. Anderson and other local researchers formed a brainstorming group at the American Museum of Natural History, developing computational techniques to model species’ requirements and distributions. Collaborating with computer scientists as a faculty member at City College of New York, Anderson has combined math and biology to predict the species that may be present at unsampled locations, reconstruct past trends, and anticipate future patterns.

Current global population demands and conservation efforts depend on estimates of species distributions (e.g., forecasting the effects of climate change on species distributions or estimating the future spread of invasive species). Because of the great need for tools that can analyze the increasing volume of available data, Dr. Anderson's research has found a huge audience of users. He is linking computer scientists, statisticians, and geographers to provide polished links between ecological theory and the advanced mathematics of machine learning.

The primary product of this line research was the Maxent (maximum entropy) method of modeling species niches and distributions (Phillips et al., 2006), a highly cited publication (over 3500 times in Google Scholar). This technique performed especially well in the largest comparison of distributional modeling techniques undertaken to date, as assessed by the National Center for Ecological Analysis and Synthesis. His later NSF-supported work has led to several papers providing insights into the principles of biological decisions necessary to meet critical assumptions of Maxent modeling. Additionally, Dr. Anderson has coauthored a book in the prestigious Princeton University Press Monographs in Population Biology series: Ecological Niches and Geographic Distributions.

Key publications:

  1. Anderson, R. P. 2013. A framework for using niche models to estimate impacts of climate change on species distributions. Annals of the New York Academy of Sciences. 1297:8–28.
  2. Peterson, A.T., J. Soberón, R. G. Pearson, R. P. Anderson, E. Martínez-Meyer, M. Nakamura, and M. B. Araújo. 2011. Ecological niches and geographic distributions. Monographs in Population Biology, 49. Princeton University Press, Princeton, NJ.
  3. Phillips, S. J., R. P. Anderson, and R. E. Schapire. 2006. Maximum entropy modeling of species geographic distributions. Ecological Modelling, 190:231–259.

ROBERT ANDERSON’S WEBSITE