PNNL

Michael Girard, a Kennewick native, is a senior data scientist in the Artificial Intelligence and Data Analytics Division within the National Security Directorate at Pacific Northwest National Laboratory. He earned his PhD in theoretical physics from the University of California, Berkeley and will soon complete a master’s degree in electrical engineering from Purdue University. While living in the Bay Area, he worked at the University of California, San Francisco Medical Center where he collaborated with the radiology, trauma, and cardiology departments, among others, to create artificial intelligence (AI) tools for medical data processing and human decision support.

Since joining PNNL, Girard has led several efforts applying AI methods to radio frequency systems. His work encompasses digital communication, signature detection, and radar technologies. Currently, he focuses on applying AI to communications and signals exploitation missions to increase the effectiveness of the U.S. warfighter. Girard also serves as the AI and autonomy lead for PNNL’s U.S. Special Operations Command subsector, as well as the technical lead for the advanced communications portfolio within the Department of Defense and Department of State sectors.

Girard resides in Richland with his wife, Danielle; their son, William; daughter, Alice; and golden retriever, Emmy. In his free time, he enjoys playing bass guitar, 3D printing accessories for his kids’ Halloween costumes, and playing ultimate frisbee.

• Artificial Intelligence
• Data Science
• Digital Signal Processing
• Wireless Communications
• Signal Exploitation
• Electronic Warfare 
• Machine Learning
• Physics

• Phd in physics, University of California, Berkeley
• MS in physics, University of California, Berkeley
• BS in physics, University of California, Irvine

E. Coda, B. Clymer, C. DeSmet, Y. Watkins and M. Girard, "Universal Fourier Attack for Time Series," in IEEE Open Journal of Signal Processing, vol. 5, pp. 858-866, 2024, doi: 10.1109/OJSP.2024.3402154. 

Shevitski, B., Watkins, Y., Man, N. and Girard, M., 2021. Digital signal processing using deep neural networks. arXiv preprint arXiv:2109.10404.

M. Girard, A. Hagen, I. Schwerdt, M. Gaumer, L. McDonald, N. Hodas, E. Jurrus, Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis, Journal of Nuclear Materials, Volume 552, 2021, 152983, ISSN 0022-3115, https://doi.org/10.1016/j.jnucmat.2021.152983.

Setzler, M., Coda, E., Rounds, J., Vann, M. and Girard, M., 2022, September. Deep Learning for Spectral Filling in Radio Frequency Applications. In 2022 Sensor Signal Processing for Defence Conference (SSPD) (pp. 1-5). IEEE.

Gihan Panapitiya, Michael Girard, Aaron Hollas, Jonathan Sepulveda, Vijayakumar Murugesan, Wei Wang, and Emily Saldanha, Evaluation of Deep Learning Architectures for Aqueous Solubility Prediction. ACS Omega 2022 7 (18), 15695-15710, DOI: 10.1021/acsomega.2c00642

Alioli, S., Dekens, W., Girard, M. et al. NLO QCD corrections to SM-EFT dilepton and electroweak Higgs boson production, matched to parton shower in POWHEG. J. High Energ. Phys. 2018, 205 (2018). https://doi.org/10.1007/JHEP08(2018)205