Address

ELEDIA@UniTN - DICAM, University of Trento

Contact Information

Call: 0461 282572

Email: marco.broccardo[at]unitn.it, marco.broccardo[at]eledia.org

Social Links

Research Interests

  • Machine learning
  • Materials-by-Design
  • Metamaterials
  • Optimization techniques
  • Periodic structures

BROCCARDO Marco

Faculty Member

ELEDIA@UNITN, University of Trento

BROCCARDO Marco is currently an Associate Professor at the University of Trento in the field of Civil Environmental and Mechanical Engineering and a member of the ELEDIA Research Center. He is habilitated/qualified to the role of Full Professor. His educational background includes a 2014 Ph.D. in Civil Engineering with a Designated Emphasis in Computational Science and Engineering from the University of California, Berkeley, where Armen Der Kiureghian advised him. He also completed two minors, one in Mechanics and one in Statistics. Before joining UC Berkeley, he obtained a Master’s degree in Civil-Structural Engineering with the highest honors (and a special mention on the curriculum) from the University of Padua, Italy. Professor Broccardo has a robust history of academic positions, including serving as an Assistant Professor at the University of Liverpool, United Kingdom, and as a Senior Researcher and Post-Doctoral Researcher at the Civil Engineering Department and Earth Science Department of ETH Zürich, Switzerland.

His academic awards are various. He holds several paper awards, a conference scholarship from Columbia University in 2013, and the Outstanding Graduate Student Instructor award from the UC Berkeley Graduate Division in 2011 (the first Italian to receive the prize in the Structural Engineering, Mechanics, and Materials program). Additionally, Broccardo was granted the prestigious UC Berkeley Graduate Division fellowship in 2009 as one of the two recipients chosen from 1,154 applicants.

Broccardo’s research is at the forefront of Reliability Theory, Uncertainty Quantification (UQ) methods, and Computational Statistics for engineering applications. His primary ambition is to synthesize physical and engineering principles with UQ and Machine Learning (ML) techniques to enhance computational models for robust predictions. His interdisciplinary research has touched various fields, but most notably, he has made significant contributions to understanding the inelastic behavior of structures under stochastic input and time-varying reliability problems such as fluid-induced seismicity in Enhanced Geothermal Systems. He also contributed significantly to Resilience Theory by modeling it as the inverse of degrading processes. Finally, he has made fundamental contributions to the use of Hamiltonian Mechanics for estimating highly reliable systems. He is the author of over 30 journal papers and more than 30 peer-reviewed conference papers.