PNNL

A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Auto-HPCnet: An Automatic Framework to Build Neural Network-based Surrogate for High-Performance Computing Applications

Physics-informed machine learning of redox flow battery based on a two-dimensional unit cell model

HT Model: Using the Molecular Transformer for predicting hydrotreating reactions

A Hybrid Deep Neural Operator/Finite Element Method for Ice-Sheet Modeling

Learning Distributed Geometric Koopman Operator for Sparse Networked Dynamical Systems

Reinforcement Learning-based Output Structured Feedback for Distributed Multi-Area Power System Frequency Control

Generative AI

Pacific Northwest National Laboratory’s Generative AI Investment aims to harness this transformative technology to drive innovation across the science, energy, and security research domains.

Advanced Memory to Support Artificial Intelligence for Science (AMAIS)

Through AMAIS, PNNL is developing new memory systems that can advance scientific computational research by broadening AI capabilities and powering high-speed analysis of large datasets.