Dr. E. Natasha Stavros is the Director of Earth Lab Analytics Hub. She specializes in complex systems science, data science, image processing, and information technologies. She developed these skills as a fire ecologist, but has applied them in other complex systems including NASA Flight Projects, biodiversity science, and urban ecology. 

She received a B.A. in Mathematics and Computer Science from the University of Colorado Boulder where her career with NASA began at the Laboratory of Atmosphere and Space Physics (LASP) doing mission operations and data analysis for data product calibration. She received a M.S. in Environmental Sustainability from the University of Edinburgh, Scotland specializing in remote observation integration into a mechanistic model to evaluate sustainable forest management practices. She completed a Ph.D. in Forest and Fire Ecology from the University of Washington linking climate, extreme fire events, and air quality degradation. She then completed a post-doc and worked as an applied science system engineer at the Jet Propulsion Laboratory, California Institute of Technology. She is an engaging public speaker and has participated in TEDx giving a talk about uncertainty under decision making and the role that's playing in our response to climate change and natural disasters.

On the heels of the data revolution, science is undergoing a model revolution to harvest scientific understanding from the modern data deluge. Modern models must scale to massive data, leverage spatiotemporal coherence in heterogeneous data, embed scientific knowledge, and answer science questions.
Deep learning has changed our modern experience, from automatically tagging your friends in your pictures, to powering autonomous vehicles that map our world. Increasingly, science applications of deep learning have enabled new insights at massive scale amidst the earth data deluge.
Modern science sometimes requires computers with much more power than is available from your average personal computer. At Earth Lab we develop and deploy our analyses in cloud environments to more easily scale our science.
Earth Lab takes a collaborative, big-data approach to answering some of our most pressing questions related to fire. We seek to understand what controls fire in the landscape, how fire is changing, and what this means for society.
In the face of increasing frequency and severity of disturbances to western U.S. forests, this effort integrates data from individual trees to entire ecoregions to advance understanding of western forest recovery.