Nick Winovich

Scientific Machine Learning

Author profile picture

Scientific Machine Learning

Sandia National Laboratories, New Mexico
P.O. Box 5800
Albuquerque, NM 87185


Nick’s research focuses on the intersection of machine learning, probability theory, and partial differential equations with an emphasis on scientific and engineering applications. Prior to joining Sandia, he directed his research toward the construction of operator networks (neural networks designed to approximate operators rather than functions) endowed with predictive uncertainty estimates to help gauge the accuracy of model predictions. His current research is concentrated on the development of reinforcement learning techniques aimed to help guide policies and design strategies involving complex physical systems.


B.A. in Mathematics, University of Notre Dame, May 2012
M.S. in Mathematics, University of Oregon, May 2015
Ph.D. in Mathematics, Purdue University, August 2021


Nickolas Winovich, Bart G van Bloemen Waanders, Deepanshu Verma, Lars Ruthotto, (2022). Reinforcement Learning for PDE Control Problems Siam Uq 2022 Document ID: 1504830

Nickolas Winovich, (2021). Deep Operator Network with Predictive Uncertainty Mechanistic Machine Learning and Digital Twins for Computational Science, Engineering & Technology Document ID: 1368313

Mohamed Salah Ebeida, Ahmed Abdelkader, Nina Amenta, Drew Philip Kouri, Ojas D. Parekh, Cynthia Ann Phillips, Nickolas Winovich, (2020). Novel Geometric Operations for Linear Programming Document ID: 1231762

Nickolas Winovich, Ahmad Rushdi, Eric T. Phipps, Jaideep Ray, Guang Lin, Mohamed Salah Ebeida, (2019). Rigorous Data Fusion for Computationally Expensive Simulations Document ID: 1009783

Showing Results. Show More Publications