Past Webinars
Past TIES Annual Meetings
TIES 2022 Annual Meeting (November 17-18, 2022)
TIES 2023 Regional Conference , Trent University, Canada (July 24-29, 2022) (Click here for playlist)
11:00 AM (CT)
U.S.
Zoom link
https://https://us06web.zoom.us/j/88576215054
Digital Twins of the Earth System and the Digital Revolution of Earth System Science
Abstract: This talk will outline three revolutions that happened in Earth system modelling in the past decades. The quiet revolution has leveraged better observations and more compute power to allow for constant improvements of prediction quality of the last decades, the digital revolution has enabled us to perform km-scale simulations on modern supercomputers that further increase the quality of our models, and the machine learning revolution has now shown that machine learned weather models are often competitive with conventional weather models for many forecast scores while being easier, smaller and cheaper. This talk will summarize the past developments, explain current challenges and opportunities, and outline how the future of Earth system modelling will look like. It will also explain why we are now talking about Digital Twins of the Earth system and how these twins will help to make Earth system modelling more interactive and flexible.
Residual Treed Gaussian Processes
11:00 AM (CT)
U.S.
Zoom link
https://us06web.zoom.us/j/83364712352
Residual Treed Gaussian Processes
Abstract: Gaussian processes (GP) enjoy wide popularity in spatial statistics, uncertainty quantification, and machine learning. With the advance of measurement technologies and increasing computing power, large numbers of measurements and large-scale numerical simulations make traditional GP models and computational strategies inadequate in dealing with spatially heterogeneous and big data, especially in multi-dimensional domains. In recent years, several multi-scale or tree-based extensions of the GP have been introduced to model spatial nonstationarity and/or achieve scalable computation. In this talk, I introduce a new Bayesian tree-based GP inference framework called residual treed GP (ResTGP). ResTGP combines key features of the treed GP (Gramacy and Lee 2008) and the multi-resolution GP (Fox and Dunson 2012), thereby enjoying the computational efficiency of the formal and the flexibility of the latter. Our main idea is to decompose a Gaussian process as well as the data at a cascade of resolutions across locations through iteratively computing predictive and residual processes, thereby characterizing the underlying covariance structure and achieving divide-and-conquer on the data points simultaneously. We also introduce a new computational strategy for Bayesian inference for ResTGP that does not rely on Metropolis-Hastings based stochastic tree search algorithms but is based on recursive message passing. This is joint work with Li Ma at Duke University.
Machine Learning in Climate Action
The use of emulators for uncertainty characterization and integrated modeling
From Theory to Practice in Anthropogenic Climate Change: More than a Century of Monitoring and Prediction
11:00 AM (CT)
U.S.
Director and Senior Scientist,
Center for International Earth Science Information Network (CIESIN)
Columbia Climate School, Columbia University
Machine learning for spatial-temporal environmental data: Successes and pitfalls
Assessing Urban Form & Climate Justice with Self Supervised Deep Learning
1:00 PM (CT)
U.S.
What is the 100 Year Flood, and Will It Be the Same in the Future
Data Science and the assessment of climate risk
Machine Learning for Climate Change and Environmental Sustainability
9:00 am (CT)
U.S.A.
INRIA Paris
Choose France Chair in AI & Research
University of Colorado Boulder
Associate Professor
Combined land use of solar energy and agriculture (Agrivoltaics) for socioeconomic and environmental co-benefits
11:00 am (CT)
U.S.A.
Combining network theory and tree functional traits to improve forest resilience to global change
11:00 am (CT)
U.S.A.
University Professor
Department of Ecology and Evolutionary Biology, University of Toronto
Machine-Learning Applications in Process-understanding and Prediction of Wildfire
Resilience Technology: Value-Added Analytics for the Wicked Wildfire Problem
11:00 am (CT)
U.S.A.
Analytics Hub Director
Earth Lab, Cooperative Institute for Research in Environmental Sciences (CIRES), University of Colorado Boulder
Leveraging global streamflow prediction systems for imputation of missing in-situ observations in West Africa
11:00 am (CT)
U.S.A.
Bayesian Inference In High-dimensional Spatial Statistics: Conquering New Challenges
Slides Available at https://cloudfil.es/jwoHd0wUgcQ
Bayesian Inference on Carbon Dioxide Surface Fluxes using Satellite Data
6:00 pm (CST)
U.S.
9:00 am (AEST)
Australia
Beyond Roughness: Efficient Parameter Estimation of Sampled Random Fields in Geology and Geophysics
Application of topological data analysis to multi-resolution matching and anomaly detection
