Data Analytics and Optimization

This is an emerging area whose predictive capability is partially based on modern data analysis and machine learning techniques rather than strictly on approximate solutions to equations that state fundamental physical principles or reduced semiempirical models. This activity encompasses a broad range of research areas and techniques, some of which are only recently coming into maturity in the context of high-end simulation.

ExaSGD

Optimizing Stochastic Grid Dynamics at Exascale

Objective: Reliable and Efficient Planning of the Power Grid

Optimize power grid planning, operation, and control and improve reliability and effi ciency

Lead: Pacific Northwest National Laboratory (PNNL)

Principal Investigators: Zhenyu (Henry) Huang, Pacific Northwest National Laboratory

CANDLE

Exascale Deep Learning–Enabled Precision Medicine for Cancer

Objective: Accelerate and Translate Cancer Research

Develop pre-clinical drug response models, predict mechanisms of RAS/RAF driven cancers, and develop treatment strategies

Lead: Argonne National Laboratory

Principal Investigators: Rick Stevens, Argonne National Laboratory

ExaBiome

Exascale Solutions for Microbiome Analysis

Objective: Metagenomics for Analysis of Biogeochemical Cycles

Discover knowledge useful for environmental remediation and the manufacture of novel chemicals and medicines

Lead: Lawrence Berkeley National Laboratory

Principal Investigators: Katherine Yelick, Lawrence Berkeley National Laboratory

ExaFEL

Data Analytics at Exascale for Free Electron Lasers

Objective: Light Source– Enabled Analysis of Protein and Molecular Structures and Design

Process data without beam time loss; determine nanoparticle size and shape changes; engineer functional properties in biology and material science

Lead: SLAC National Accelerator Laboratory

Principal Investigators: Amedeo Perazzo, SLAC National Accelerator Laboratory