Statistics and Machine Learning in Materials Modeling
TITLE:
Statistics and Machine Learning in Materials Modeling
DATE:
Friday, July 31, 2020
TIME:
3:00 PM
LOCATION:
Virtual Zoom Conference
SPEAKER:
Dr. Ramin Bostanabad, Mechanical and Aerospace Engineering, University of CA, Irvine
ABSTRACT:
Engineered materials are an indispensable part of our modern life with far-reaching applications that include aerial and ground transportation, large-scale structures, national security, and medicine. The ever-evolving societal, environmental, and cultural awareness calls for significantly complex materials systems with unprecedented properties and functionalities that reliably meet stakeholders’ demands under extreme conditions. The overarching goal of my research is to statistically and mathematically model these complexities and, in turn, accelerate the development and deployment of engineered materials.
In this talk, I will first discuss the challenges that motivate the research at PMACS lab which primarily include multiscale and multi-physics nature, presence of spatiotemporally varying and coupled uncertainty sources, lack of knowledge and computational resources, and high dimensionality. Then, I will introduce the frameworks and methods that we have developed to address these challenges via discipline-agnostic, data-driven, physics-aware, and modular solutions.
Bio: Dr. Ramin Bostanabad received his Ph.D. from Northwestern University in February 2019. He joined the Department of Mechanical and Aerospace Engineering at UCI in September 2019 and founded the
Probabilistic Modeling and Analysis of Complex Systems (PMACS) laboratory.
At PMACS lab, Dr. Bostanabad’s group develops computational framework and tools for analyzing and designing complex systems such as advanced manufacturing processes and multiscale materials. These contributions are on the interface of statistics, machine learning, and mechanics and include data-driven microstructure characterization, multi-scale materials modeling with deep learning and random processes, inverse system identification with hierarchical evolutionary programming, and assimilation of multiple data sources with Bayesian statistics.
HOST:
Satchi Venkataraman
VIDEO: