Grant to help SUNY Poly professor, students improve resiliency of bridges, buildings during earthquakes
MARCY— The State University of New York Polytechnic Institute has announced that Associate Professor of Civil Engineering Dr. Sivapalan Gajan has received $198,000 in funding from the National Science Foundation to work on an effort to improve the resiliency of buildings and bridges during earthquakes.
The research combines physics with data science, leveraging computational modeling, simulations, and machine learning capabilities to develop a greater predictive framework to enable engineers to design more effective rocking systems for foundations of these structures to reduce human and economic losses from earthquakes.
“On behalf of SUNY Poly, I am excited to congratulate Professor Gajan for his research that has not only resulted in this recognition by the National Science Foundation, but will also provide exciting experiential learning opportunities for students and provide the data necessary to improve rocking foundations and potentially save lives,” said Interim Dean of the College of Engineering Dr. Michael Carpenter.
“I am thrilled to receive this grant from the NSF as we seek a data-driven approach to enhance the structural integrity of buildings by knowing the ways in which rocking foundations can be optimized to minimize damage during an earthquake or other disaster,” said Gajan.
“The project will use existing experimental data from around the world to develop new algorithms by combining mechanics with data science,” Gajan added. “This will provide a fertile educational platform for SUNY Poly students to gain hands-on experience finding solutions to the structural questions we are exploring, which can lead to less damage, less loss of life, and lower costs to rebuild.”
Multiple SUNY Poly civil engineering and mechanical engineering undergraduate students will be able to work on this project at SUNY Poly’s campus in Marcy.
The students will participate on the numerical modeling aspects of the effort, as well as on the development of machine learning models for the performance of soil-foundation-structure systems, providing them with a unique learning opportunity, as well as direct exposure to engineering research.
The novel, hybrid predictive framework will have the potential to continuously learn, adapt, and improve in the future as additional data is collected and integrated to provide more valuable feedback over time, the announcement added.