CSL Master Calendar

View Full Calendar

DCL Seminar: Christopher K. Wikle - An Integration of Deep Neural Networks and Deep Hierarchical Dynamic Statistical Models for Parsimonious Spatio-Temporal Forecasting

Event Type
Seminar/Symposium
Sponsor
Decision and Control Laboratory, Coordinated Science Laboratory
Location
CSL Auditorium, Room B02
Date
Apr 10, 2019   3:00 pm  
Speaker
Christopher K. Wikle, Ph.D., University of Missouri
Contact
Linda Stimson
E-Mail
ls9@illinois.edu
Phone
217-333-9449
Views
214
Originating Calendar
CSL Decision and Control Group

Decision and Control Laboratory

Coordinated Science Laboratory

 

“An Integration of Deep Neural Networks and Deep Hierarchical Dynamic Statistical Models for Parsimonious Spatio-Temporal Forecasting”


Christopher K. Wikle, Ph.D.

Curators’ Distinguished Professor and Chair
University of Missouri

 

Wednesday, April 10, 2019

3:00pm – 4:00pm

CSL Auditorium (B02)

____________________________________________________________________________________________________________________________________________________________________

Abstract:
Spatio-temporal data are ubiquitous in the sciences and engineering, and their study is important for understanding and predicting a wide variety of processes. One of the difficulties with statistical modeling of spatial processes that change in time is the complexity of the dependence structures that must describe how such a process varies, and the presence of high-dimensional complex datasets and large prediction domains. It is particularly challenging to specify parameterizations for nonlinear dynamic spatio-temporal models (DSTMs) that are simultaneously useful scientifically and efficient computationally. Statisticians have developed multi-level (deep) hierarchical models that can accommodate process complexity as well as the uncertainties in the predictions and inference. However, these models can be expensive and are typically application specific. On the other hand, the machine learning community has developed alternative “deep learning” approaches for nonlinear spatio-temporal modeling. These models are flexible yet are typically not implemented in a probabilistic framework. The two paradigms have many things in common and suggest hybrid approaches that can benefit from elements of each framework. This talk presents a brief introduction to the multi-level (deep) hierarchical DSTM (H-DSTM) framework, and deep models in machine learning, culminating with the deep neural DSTM (DN-DSTM).  Particular focus will be on recent statistical approaches that combine elements from H-DSTMs and echo state network DN-DSTMs that are very parsimonious, computationally efficient and provide effective solutions for long-lead forecasting problems in environmental statistics.

Bio:

Christopher K. Wikle is Curators’ Distinguished Professor and Chair of Statistics at the University of Missouri (MU), with additional appointments in Soil, Environmental and Atmospheric Sciences and the Truman School of Public Affairs.  He received a PhD co-major in Statistics and Atmospheric Science in 1996 from Iowa State University.  He was research fellow at the National Center for Atmospheric Research from 1996-1998, after which he joined the MU Department of Statistics.  His research interests are in spatio-temporal statistics applied to environmental, ecological, geophysical, agricultural and federal survey applications, with particular interest in dynamics.  His work has been concerned with formulating computationally efficient deep hierarchical Bayesian models motivated by scientific principles, with more recent work at the interface of deep neural models in machine learning.   Awards include elected Fellow of the American Statistical Association (ASA), elected Fellow of the International Statistical Institute (ISI), Distinguished Alumni Award from the College of Liberal Arts and Sciences at Iowa State University, ASA Environmental (ENVR) Section Distinguished Achievement Award, co-awardee 2017 ASA Statistical Partnership Among Academe, Industry, and Government (SPAIG) Award, the MU Chancellor’s Award for Outstanding Research and Creative Activity in the Physical and Mathematical Sciences, the Outstanding Graduate Faculty Award, and Outstanding Undergraduate Research Mentor Award.  His book Statistics for Spatio-Temporal Data (co-authored with Noel Cressie) was the 2011 PROSE Award winner for excellence in the Mathematics Category by the Association of American Publishers and the 2013 DeGroot Prize winner from the International Society for Bayesian Analysis.  His latest book, Spatio-Temporal Statistics with R, with Andrew Zammit-Mangion and Noel Cressie, was published in 2019 and is free to download at spacetimewithR.org.   He is Associate Editor for several journals and is one of six inaugural members of the Statistics Board of Reviewing Editors for Science.

link for robots only