Artificial Intelligence Crosscut

The Artificial Intelligence crosscut is developing novel AI methods for scientific computing, using AI methods to improve our software, and delivering AI capabilities to applications across the Department of Energy.

• Development of AI methods advances the mathematical foundations of AI for scientific computing. This work includes the construction of surrogate models and physics-constrained methods that embed problem-specific information to reduce the space of feasible solutions, designing novel neural network architectures tailored to scientific problems, and providing hyperparameter optimization to make these methods practical at scale.

• Usage of AI methods integrates AI techniques into our core numerical capabilities to deliver speedups and new capabilities where traditional approaches fall short.  This work includes applying AI to accelerate linear, nonlinear, and eigenvalue solves using AI surrogates and enhanced preconditioners, and reinforcement learning; to improve graph partitioning for load-balanced parallel computation; to advance numerical optimization and uncertainty quantification using active learning, probabilistic learning of manifolds, and Bayesian neural network surrogates; and to advance the mathematics for digital twins by optimizing data acquisition and fidelity.

• Delivery of AI capabilities ensures these advances reach our many SciDAC application partners and provide reliable tools to accelerate their science.