PNNL

Himanshu Sharma joined Pacific Northwest National Laboratory (PNNL) in 2020 as a research scientist in the Optimization and Controls group. He possesses in-depth expertise in computational modeling and simulations for complex physical systems, advanced data-driven machine learning methods, and high-performance computing. Sharma holds a PhD in mechanical engineering from Iowa State University, with a research focus on developing a data-driven Perron-Frobenius operator-based framework for sensor placement for monitoring indoor air quality under uncertainty. Prior to joining PNNL, Sharma served as a postdoctoral scholar at the Argonne Leadership Computing Facility, Argonne National Laboratory, where he contributed to the development and deployment of probabilistic neural networks for scientific applications at scale, particularly in understanding and analyzing challenges associated with distributed training of neural networks capable of predicting uncertainties. His research interests encompass physics-informed machine learning, reinforcement learning, uncertainty quantification, computational fluid dynamics, and dynamics and control for complex physical systems, including energy systems and smart building systems.

• Dynamical Systems and Controls
• Physics-Informed Machine Learning
• Uncertainty Quantification
• Optimization
• Computational Fluid Dynamics

• PhD in mechanical engineering, Iowa State University
• MS in technology, Indian Institute of Technology
• BS in mechanical engineering, Institute of Technology

• Outstanding Performance Award, PNNL, 2022
• Outstanding Performance Award, PNNL, 2020
• Best Paper Award, American Control Conference, by Energy Systems Technical Committee, American Society of Mechanical Engineering

2024

• Sinha S., H. Sharma, and M.B. Shrivastava. 2024. "Application of advanced causal analyses to identify processes governing secondary organic aerosols." Scientific Reports 14, no. _:Art. No. 10718. PNNL-SA-175592. doi:10.1038/s41598-024-59887-7

2023

• Schram M., K. Rajput, K. Somayaji NS, P. Li, J. St. John, and H. Sharma. 2023. "Uncertainty aware machine-learning-based surrogate models for particle accelerators: Study at the Fermilab Booster Accelerator Complex." Physical Review Accelerators and Beams 26, no. 4:Art. No. 044602. PNNL-SA-190245. doi:10.1103/PhysRevAccelBeams.26.044602
• Sharma H., L.D. Marinovici, V.A. Adetola, and H.T. Schaef. 2023. "Data-Driven Modeling of Power Generation for a Coal Power Plant Under Cycling." Energy and AI 11. PNNL-SA-171444. doi:10.1016/j.egyai.2022.100214
• Sharma H., M.B. Shrivastava, and B. Singh. 2023. "Physics informed deep neural network embedded in a chemical transport model for the Amazon rainforest." npj Climate and Atmospheric Science 6, no. 2023:2. PNNL-SA-172595. doi:10.1038/s41612-023-00353-y

2021

• Bhattacharya A., S.S. Vasisht, V.A. Adetola, S. Huang, H. Sharma, and D.L. Vrabie. 2021. "Control Co-Design of Commercial Building Chiller Plant using Bayesian Optimization." Energy and Buildings 246. PNNL-SA-158439. doi:10.1016/j.enbuild.2021.111077
• Bhattacharya S., H. Sharma, and V.A. Adetola. 2021. "Towards Learning-Based Architectures for Sensor Impact Evaluation in Building Controls." In Proceedings of the Twelfth ACM International Conference on Future Energy Systems (e-Energy '21), June 28-July 2, 2021, Virtual, Online, 493-498. New York, New York:Association for Computing Machinery. PNNL-SA-161319. doi:10.1145/3447555.3466591
• Sharma H., U. Vaidya, and B. Ganapathysubramanian. 2021. "Contaminant Source Identification from Finite Sensor Data: Perron-Frobenius Operator and Bayesian Inference." Energies 14, no. 20:Art. No. 6729. PNNL-SA-156588. doi:10.3390/en14206729
• Sharma H., V.A. Adetola, L.D. Marinovici, and H.T. Schaef. 2021. "DATA DRIVEN APPROACH TO ANALYZING THE IMPACT OF POWER PLANT CYCLING ON AIR PREHEATER DEGRADATION AND REMAINING USEFUL LIFE." In ASME Turbo Expo 2021: Turbomachinery Technical Conference and Exposition, June 7-11, 2021, Virtual, Online, Volume 9B, Paper No: GT2021-59914, V09BT26A013. New York, New York:ASME. PNNL-SA-158306. doi:10.1115/GT2021-59914