Mechanical and Civil Engineering Seminar

Increased availability of large amounts of data, development of new sensing technologies and connected systems such as the Internet of Things have generated tremendous interest in the development of methods to learn from data. In parallel, engineers have a long history of building high-fidelity models, based on physical principles, that allow us to model the behavior of highly complex systems. This talk aims at presenting some of the exciting research opportunities that arise at the intersection of these two topics, data analytics and high-fidelity modeling, and illustrate potential applications.
For instance, our civil engineering community is facing complex challenges caused by an increased urbanization or the uncertainties related to climate change, yielding a need for more resilient and sustainable infrastructure. Data sensing and analysis can be leveraged to monitor our existing infrastructure, or to design more sustainable and resilient urban systems.  For instance, system identification schemes can be used in conjunction with high-fidelity models to monitor the behavior of dynamical systems and predict the future behavior of potentially damaged systems. Bayesian inference algorithms are particularly interesting in this framework as they allow quantification of uncertainties around the estimated quantities of interest, where large uncertainties can arise when the data is not highly informative or the inputs are stochastic. However, the high computational complexity of Bayesian algorithms makes them cumbersome to use for inference in large dimensional systems, and this talk will present some algorithmic enhancements that achieve a good trade-off between accuracy and computational cost.
The combination of data-mining and physics-based modeling also finds applications in various engineering fields. In the materials sciences for instance, machine learning algorithms can be used in conjunction with experiments or high-fidelity simulations to obtain a better understanding of structure-property-performance linkages. Very interestingly, the application of machine learning algorithms to engineering problematics gives rise to challenging problematics and technical questions, for example the need to accurately quantify uncertainties through machine learning pipelines, or handling small amounts of data. This talk thus aims at illustrating some of the challenges and opportunities related to the use of both model-based and data-based learning algorithms for engineering applications.