Machine learning tools to aid in solving complex problems of interest to nuclear national security
Career planning can be challenging, and it is one of those things in life that, although important, are not taught at school. In this presentation, I will share my personal experience as a student that came from abroad for graduate school at UF MAE, how I built my connection with the Nuclear National Security Administration (NNSA) national laboratories, and how my early career as a data scientist started. Machine learning (ML) is undoubtedly a current hot topic however its definition is still in the making and scientists are reluctant to trust black boxes. So far in my career I consistently used flavors of ML for prediction and data processing taking advantage of the application versatility of these methods to different complex physical problems. I will summarize my recent work as a graduate student at UF and as a postdoc at Los Alamos National Laboratory (LANL) highlighting the tools used that I found to be the most attractive for getting a job at national laboratories nowadays: (i) Multi-fidelity surrogate models to quantify the amplification of the particle departure from axisymmetry during multiphase detonations; (ii) Recurrent neural networks to predict the evolution of damage in high strain brittle fracture; (iii) Sparse principal component analysis to understand entangled relationships between design variables in inertial confinement fusion.
Giselle is a simulation data scientist for Above and Below-Ground Physics in the Atmospheric Science Research and Applications group at the Lawrence Livermore National Laboratory’s Physical Life Science directorate. Her current work focuses on machine learning and uncertainty quantification approaches applied to atmospheric flow, transport & hazard assessment. Giselle received her bachelor’s degree in nuclear engineering from Balseiro Institute, San Carlos de Bariloche, Rio Negro, Argentina in June 2014. Her thesis was focused on the surveillance program for the Argentinian reactor CAREM 25. She received her master’s degree in mechanical engineering from the University of Florida in December 2016. She received her Ph.D. in aerospace engineering from the University of Florida in December 2018. She was under the supervision of Dr. Raphael T. Haftka and Dr. S. Balachandar. Her thesis topic was on the quantification of particle departure from axisymmetry in multiphase cylindrical detonations. She was a postdoctoral research associate in the Verification and Analysis Group, X Computational Group at Los Alamos National Laboratory working on machine learning applied to fracture mechanics and inertial confinement fusion physics.
UF MAE SGT Seminar Series