StatEcoNet: Statistical Ecology Neural Networks for Species Distribution Modeling

Authors

  • Eugene Seo Oregon State University
  • Rebecca A. Hutchinson Oregon State University
  • Xiao Fu Oregon State University
  • Chelsea Li Oregon State University
  • Tyler A. Hallman Swiss Ornithological Institute, Sempach, Switzerland
  • John Kilbride Oregon State University
  • W. Douglas Robinson Oregon State University

Keywords:

Energy, Environment & Sustainability

Abstract

This paper focuses on a core task in computational sustainability and statistical ecology: species distribution modeling (SDM). In SDM, the occurrence pattern of a species on a landscape is predicted by environmental features based on observations at a set of locations. At first, SDM may appear to be a binary classification problem, and one might be inclined to employ classic tools (e.g., logistic regression, support vector machines, neural networks) to tackle it. However, wildlife surveys introduce structured noise (especially under-counting) in the species observations. If unaccounted for, these observation errors systematically bias SDMs. To address the unique challenges of SDM, this paper proposes a framework called StatEcoNet. Specifically, this work employs a graphical generative model in statistical ecology to serve as the skeleton of the proposed computational framework and carefully integrates neural networks under the framework. The advantages of StatEcoNet over related approaches are demonstrated on simulated datasets as well as bird species data. Since SDMs are critical tools for ecological science and natural resource management, StatEcoNet may offer boosted computational and analytical powers to a wide range of applications that have significant social impacts, e.g., the study and conservation of threatened species.

Downloads

Published

2021-05-18

How to Cite

Seo, E., Hutchinson, R. A., Fu, X., Li, C., Hallman, T. A., Kilbride, J., & Robinson, W. D. (2021). StatEcoNet: Statistical Ecology Neural Networks for Species Distribution Modeling. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 513-521. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16129

Issue

Section

AAAI Technical Track on Application Domains