The recipient of the 2017 Nevada Medal for Distinguished Graduate Student Paper in Bridge Engineering is Sujith Mangalathu, a doctoral student at Georgia Tech.
The Nevada Medal is an annual award given to a graduate student paper that has made significant contributions to the state-of-the-art in bridge engineering.
The title of the winning paper is: "Machine Learning Techniques to Identify the Critical Uncertainty Parameters Influencing the Seismic Performance of Bridges." Critical uncertain variables influencing the seismic demand in bridge components are identified through various regression analyses and machine learning techniques, and a multi-parameter fragility model is proposed.
"I am humbled, honored, and grateful to have been selected as a recipient of the prestigious Nevada Medal for Distinguished Graduate Student Paper in Bridge Engineering for 2017," Mangalathu said. "I would like to express my sincere gratitude to the Civil Engineering department at the University of Nevada, Reno for bestowing me with such an honor."
Mangalathu's research has been directed by Dr. Reginald DesRoches and Jamie Padgett. Evaluators of the entries were from a group of experts in bridge engineering research and design. The award includes a plaque, an engraved 14-K gold-plated pin, and a $1,500 check. The funding for the award was initially provided through an endowment established by Simon Wong Engineering of San Diego, California. Wong completed a bachelor's degree ('79) and master's ('84) degree in civil engineering at the University of Nevada, Reno.
The award is currently sponsored by the Civil and Environmental Engineering Department and coordinated by Saiid Saiidi, professor of civil and environmental engineering.
Mangalathu intends to continue his work on developing a robust framework which uses machine learning techniques for the performance based risk assessment of bridge systems subjected to natural and man-made hazards.
Machine Learning Techniques to Identify the Critical Uncertainly Parameters Influencing the Seismic Performance of Bridges
Recent efforts of regional seismic risk assessment of structures often pose a challenge in dealing with the potentially variable uncertain input parameters. The source of uncertainties can be either epistemic or aleatoric. This article identifies uncertain variables exhibiting strongest influences on the seismic demand of bridge components through various regression and machine learning techniques such as linear, stepwise, Ridge, Lasso, and elastic net regressions. As the sensitivity study identifies more than one significant variable, a multi-parameter fragility model using Lasso regression is suggested in this paper. The proposed fragility methodology is able to identify the relative impact of each uncertain input variable and level of treatment needed for these variables in the estimation of seismic demand models and fragility curves. Thus, the proposed approach helps bridge owners to spend their resources judiciously (e.g. data collection, field investigations, censoring) in the generation of a more reliable database for the regional risk assessment.