Machine learning for computational sustainability

To avoid ecological collapse, we must manage Earth's ecosystems sustainably. Viewed as a control problem, the two central challenges of ecosystem management are to acquire a model of the system that is sufficient to guide good decision making and then optimize the control policy against that model. This paper describes three efforts aimed at addressing the first of these challenges-machine learning methods for modeling ecosystems. The first effort focuses on automated quality control of environmental sensor data. Next, we consider the problem of learning species distribution models from citizen science observational data. Finally, we describe a novel approach to modeling the migration of birds. A major challenge for all of these methods is to scale up to large, spatially-distributed systems.

I. Extended Abstract

The world-wide spread and rapid growth of human populations has resulted in large changes in the functioning of the earth's ecosystems. There has been a huge conversion of land to agricultural production and, consequently, large decreases in the range and size of the populations of many species.