Please join the Notre Dame Environmental Change Initiative for a seminar presented by Stefano Castruccio, Associate Professor in the Department of Applied and Computational Mathematics and Statistics at the University of Notre Dame.
The title of his talk is "Artificial Intelligence Spatio-Temporal Modeling of Environmental Data".
Please RSVP if you plan to attend the talk. Lunch will be provided.
Abstract: The main aim of this talk is to showcase the role of computationally affordable spatio-temporal models, especially stochastic machine learning models, to aid some of the most relevant scientific investigations ranging from air pollution citizen science data monitoring to assessment of wind energy resources. While the applications differ in their aim, neural networks, and especially stochastic versions such as reservoir computing methods, can be used to provide fast and accurate predictions. In the second part of my talk, I will also discuss some of my recent research on how to successfully integrate physical information to machine learning methods to provide an improved characterization of fluid motion.
Bio: Stefano Castruccio's main area of research focuses on the development of spatio-temporal models for environmental applications, with applications spanning from assessment of renewable energy resources to assessing mortality from air pollution. His focus is mostly on climate and weather modes, and the use of statistical models that can act as a stochastic approximation to provide computationally affordable uncertainty quantification.
Originally published at environmentalchange.nd.edu.