Toward Accelerating Discovery via Physics-Driven and Interactive Multifidelity Bayesian Optimization

Journal Article · 05 November 2024 · Journal of Computing and Information Science in Engineering

DOI: https://doi.org/10.1115/1.4066856 · OSTI ID:2499566

Biswas, Arpan ^[1]; Valleti, Mani ^[1]; Vasudevan, Rama ^[2]; Ziatdinov, Maxim ^[3]; Kalinin, Sergei V. ^[4]

---

1. University of Tennessee, Knoxville, TN (United States)
2. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
3. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
4. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); University of Tennessee, Knoxville, TN (United States)

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and often nondifferentiable parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of combinatorial libraries, processing spaces, and molecular embedding spaces. Often these systems are expensive or time consuming to evaluate a single instance, and hence classical approaches based on exhaustive grid or random search are too data intensive. This resulted in strong interest toward active learning methods such as Bayesian optimization (BO) where the adaptive exploration occurs based on human learning (discovery) objective. However, classical BO is based on a predefined optimization target, and policies balancing exploration and exploitation are purely data driven. In practical settings, the domain expert can pose prior knowledge of the system in the form of partially known physics laws and exploration policies often vary during the experiment. Here, we propose an interactive workflow building on multifidelity BO (MFBO), starting with classical (data-driven) MFBO, then expand to a proposed structured (physics-driven) structured MFBO (sMFBO), and finally extend it to allow human-in-the-loop interactive interactive MFBO (iMFBO) workflows for adaptive and domain expert aligned exploration. These approaches are demonstrated over highly nonsmooth multifidelity simulation data generated from an Ising model, considering spin–spin interaction as parameter space, lattice sizes as fidelity spaces, and the objective as maximizing heat capacity. Detailed analysis and comparison show the impact of physics knowledge injection and real-time human decisions for improved exploration with increased alignment to ground truth. Here, the associated notebooks allow to reproduce the reported analyses and apply them to other systems.

• Research Organization: University of Washington, Seattle, WA (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)
• Grant/Contract Number: SC0019288
• OSTI ID: 2499566
• Journal Information: Journal of Computing and Information Science in Engineering, Journal Name: Journal of Computing and Information Science in Engineering Journal Issue: 12 Vol. 24; ISSN 1530-9827
• Publisher: ASMECopyright Statement
• Country of Publication: United States
• Language: English