This event has been canceled for 3/22 and will be rescheduled for later in the spring term.

Title: Data Integration across Scales: Bayesian Methods and Zonation Approaches

Abstract: Subsurface research has been pioneering statistical and machine learning methods to characterize spatiotemporal variability across scales, particularly focused on uncertainty quantification and the use of correlated/proxy variables. These methods can be applied and extended in other environmental applications. This talk will focus on the two methods: (1) Bayesian methods with Gaussian process models to integrate disparate datasets with different scales and accuracies, and (2) zonation approaches to map co-varied heterogeneous properties. Three applications will be presented: (1) mapping co-varied bedrock-to-canopy properties based on airborne remote sensing data in mountainous watersheds, (2) mapping regional-scale radiation levels based on airborne and ground-based surveys in the Fukushima region, and (3) developing long-term in situ monitoring strategies for groundwater contamination.

Speaker bio: Haruko Wainwright is the Mitsui Career Development Professor in Contemporary Technology; Assistant Professor in the Department of Nuclear Science and Engineering, and the Department of Civil and Environmental Engineering at Massachusetts Institute of Technology. She received nuclear engineering in 2006, MA in statistics in 2010 and PhD in nuclear engineering in 2010 from University of California, Berkeley. Before joining MIT, she was a Staff Scientist in the Earth and Environmental Sciences Area at Lawrence Berkeley National Laboratory. Her research focuses on environmental informatics, aiming to improve understanding and predictions in Earth and environmental systems through mechanistic modeling and machine learning.

About the series: The MIT Earth  Resources Laboratory's Friday Informal Seminar Series (FISH) features presentations by our lab members as well as special guests from academia and the energy industry on our areas of interest including geothermal energy, carbon sequestration, machine learning for geophysics, multiphase flow, subsurface imaging, and uncertainty quantification. Titles and abstracts will be posted here when available. For more info or Zoom password please contact erl-info@mit.edu.