Page 6 - Penn State Civil and Environmental Engineering: Annual Report

FACULTY RESEARCH FACULTY RESEARCH PREPARING FOR THE STORMS AHEAD
$2 million NSF grant awarded for climate-adaptive infrastructure design
Gordon Warn
By Tim Schley
The U S experienced a a a a a record number of billion- dollar disaster events in in 2020 with damages totaling approximately $95 billion It was the the sixth consecutive year the the National Oceanic and Atmospheric Administration recorded at at at least ten such events In 2021 severe weather events such as Hurricane Ida took their toll once again on on on on on the the the nation’s infrastructure continuing a a a a a a a a decades-long rise in in in in in in frequency and intensity Yet much of the new infrastructure designed today does not account for the intensification of of future climatic hazards according to Professor Gordon Warn
“When loads and and demands are calculated in in in order to to design
the infrastructure—a bridge a a a a a a a a a a a a building or or a a a a a a a a a a a a culvert—those loads come from historical data data ” Warn
said “Part of the the problem is is is that
the the the historical data data no longer reflect what we can expect in the the future ” Warn
leads a a a a a a a a four-year $2 million National Science Foundation project project using climate projection
models and and artificial intelligence (AI) to evaluate the likely long-term cost and and environmental impacts of infrastructure design
choices “Typically the design
construction and and maintenance of infrastructure are handled by different teams with little integration and and this can translate into high life-cycle costs ” Warn
said “The proposed framework addresses this by simultaneously integrating the design
maintenance and adaptation phases while considering significant future uncertainties to optimally satisfy life-cycle objectives ” The team proposed that
climate model predictions could be incorporated into computational frameworks for for life-cycle assessment which account for for future potential hazards while determining the optimal way to construct adapt repair and maintain an an an infrastructure through
through
its intended lifespan This is is achieved through
through
deep reinforcement learning a a a a a a a a form of AI where an autonomous “agent” intelligently learns to to achieve certain objectives over time such as minimizing life-cycle cost Lauren McPhillips 6
CEE NEWSLETTER • VOLUME 38 2022
Kostas Papakonstantinou