Uncovering Ecological Patterns with Convolutional Neural Networks

Philip G Brodrick; Andrew B Davies; Gregory P Asner

doi:10.1016/j.tree.2019.03.006

Uncovering Ecological Patterns with Convolutional Neural Networks

Trends Ecol Evol. 2019 Aug;34(8):734-745. doi: 10.1016/j.tree.2019.03.006. Epub 2019 May 8.

Authors

Philip G Brodrick¹, Andrew B Davies², Gregory P Asner³

Affiliations

¹ Center for Global Discovery and Conservation Science, Arizona State University, Tempe, AZ 85281, USA; Department of Global Ecology, Carnegie Institution for Science, 260 Panama Street, Stanford, CA 94305, USA. Electronic address: brodrick@alumni.stanford.edu.
² Center for Global Discovery and Conservation Science, Arizona State University, Tempe, AZ 85281, USA; Department of Global Ecology, Carnegie Institution for Science, 260 Panama Street, Stanford, CA 94305, USA; Present address: Department of Organismic and Evolutionary Biology, Harvard University, 22 Divinity Ave, Cambridge, MA 02138, USA. Electronic address: https://twitter.com/andrewbdavies.
³ Center for Global Discovery and Conservation Science, Arizona State University, Tempe, AZ 85281, USA; Department of Global Ecology, Carnegie Institution for Science, 260 Panama Street, Stanford, CA 94305, USA. Electronic address: https://twitter.com/greg_asner.

PMID: 31078331
DOI: 10.1016/j.tree.2019.03.006

Abstract

Using remotely sensed imagery to identify biophysical components across landscapes is an important avenue of investigation for ecologists studying ecosystem dynamics. With high-resolution remotely sensed imagery, algorithmic utilization of image context is crucial for accurate identification of biophysical components at large scales. In recent years, convolutional neural networks (CNNs) have become ubiquitous in image processing, and are rapidly becoming more common in ecology. Because the quantity of high-resolution remotely sensed imagery continues to rise, CNNs are increasingly essential tools for large-scale ecosystem analysis. We discuss here the conceptual advantages of CNNs, demonstrate how they can be used by ecologists through distinct examples of their application, and provide a walkthrough of how to use them for ecological applications.

Keywords: convolutional neural network; deep learning; image segmentation; machine learning; object detection; remote sensing.

Publication types

Research Support, Non-U.S. Gov't
Review

MeSH terms

Ecology
Ecosystem*
Image Processing, Computer-Assisted
Neural Networks, Computer*