Shashank Subramanian
Computer Systems Engineer 4
National Energy Research Scientific Computing Center (NERSC)
Science Engagement & Workflows Dept.
Data & AI Services Group
Shashank Subramanian is a deep learning engineer at NERSC with research interests in the intersection of high-performance scientific computing, deep learning, and physical sciences. His current research involves developing large-scale neural network surrogates for high resolution, data-driven weather and climate simulations and on algorithmic developments to understand and improve physics-based neural operators. Prior to joining NERSC, Shashank received his PhD in Computational Sciences and Applied Mathematics from UT Austin in 2021. His doctoral research focused on integrating mathematical models of cancer growth with patient-specific imaging data using efficient parallel algorithms, optimization methods, and high-performance computing software to improve personalized medicine. Shashank received his Bachelors in Aerospace Engineering from the Indian Institute of Technology Madras in 2016.
Recent Publications
Ensemble Inversion for Brain Tumor Growth Models With Mass Effect
Authors: Subramanian, S; Ghafouri, A; Scheufele, KM; Himthani, N; Davatzikos, C; Biros, G
April 2023, IEEE Transactions on Medical Imaging
Comprehensive Performance Modeling and System Design Insights for Foundation Models
Authors: Subramanian, S; Rrapaj, E; Harrington, P; Chheda, S; Farrell, S; Austin, B
November 2024
FourCastNet: Accelerating Global High-Resolution Weather Forecasting Using Adaptive Fourier Neural Operators
Authors: Kurth, T; Subramanian, S; Harrington, P; Pathak, J; Mardani, M; Hall, D
June 2023
Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior
Authors: Subramanian, S; Harrington, P; Keutzer, K; Bhimji, W; Morozov, D; Mahoney, M
December 2023, Advances in Neural Information Processing Systems
More By Shashank Subramanian