1. Home
  2. Report Archives
  3. Project Highlights -2020
  4. High-Performance Computing, Simulation, and Data Science
  5. Hypothesis Testing via Artificial Intelligence: Generating Physically Interpretable Models of Scientific Data with Machine Learning

Hypothesis Testing via Artificial Intelligence: Generating Physically Interpretable Models of Scientific Data with Machine Learning

Brenden Petersen | 19-DR-003

Executive Summary

We will enable hypothesis testing via artificial intelligence by (1) rapidly generating and testing hypotheses with machine learning; and (2) extracting physical insights and guiding the scientific process. This revolutionary approach will accelerate design-build-test iterations with application across the Department of Energy's and National Nuclear Security Administration's mission space, including stockpile stewardship, advanced manufacturing, and weather pattern prediction.

Publications, Presentations, and Patents

Kim, S., et al. 2020. "A Demonstration Platform for Deep Symbolic Regression." International Joint Conferences on Artificial Intelligence 2020 (online), January 2021. LLNL-CONF-805899