SimCenter, Berkeley Undergrads Develop Algorithm to Predict Natural Hazards



This semester, four UC Berkeley undergraduate students are exploring the potential of machine learning to generate real-time predictions of natural hazard events. Through internships with the NHERI SimCenter, students Rohil Kanwar, Michael Leite-Garcia, Michelle Gu, and Maxwell Liu are testing a wide range of techniques to see if they can improve predictive modeling for storm surges. Dr. Matt Schoettler, SimCenter Associate Director, and Dr. Ajay B. Harish of the SimCenter development team, have provided guidance to the students and their projects.

“Rohil is exploring the prediction using similarity scores to train Convolutional Neural Networks (CNNs), Michael is developing Physics-Informed Neural Networks (PINN), Michelle is developing Generative Adversarial Networks (GANs) which are often used in computer vision, and Maxwell is combining Gaussian processes with neural networks," said Harish, who is also a postdoctoral researcher with Professor Sanjay Govindjee, and recently taught a course on engineering dynamics for the department. He added, "we are very excited to see how the techniques compare toward enhancing the predictive modeling capabilities for natural hazard events."

The students speak to the real world change they hope to have through their internships. Gu, a third-year student majoring in Data Science, shared, "I want to work on projects that make a true impact, and this opportunity with the SimCenter aligned perfectly with that goal and my high school background in Global Ecology. I have gained a tremendous amount of knowledge in data science and machine learning from interacting with the other team members and Dr. Harish, and I'm excited about the possibilities with all the projects Dr. Harish is working on. I can't wait to see all our final products in action and making an impact.”

Kanwar, a fourth-year student also majoring in Data Science, added, "this project seeks to actually save lives using real-time intelligent information dispersal using the technology that we are building, and that thought empowers me to think about innovative solutions where deep learning could bring about life-altering impact."

These internships were made possible by UC Berkeley's Data Science Discovery Program, which brings together multidisciplinary teams for cutting-edge data research.