Machine Learning and Ecosystem Informatics: Challenges and Opportunities

Abstract

Ecosystem Informatics is the study of computational methods for advancing the ecosystem sciences and environmental policy. This talk will discuss the ways in which machine learning—in combination with novel sensors—can help transform the ecosystem sciences from small-scale hypothesis-driven science to global-scale data-driven science. Example challenge problems include optimal sensor placement, modeling errors and biases in data collection, automated recognition of species from acoustic and image data, automated data cleaning, fitting models to data (species distribution models and dynamical system models), and robust optimization of environmental policies. The talk will also discuss the recent development of The Evidence Tree Methodology for complex machine learning applications.