Adaptive Computing for Scale-Up Problems
Kevin Patrick Griffin, Hilary Egan, Marc Henry de Frahan, Juliane Mueller, Deepthi Vaidhynathan, Dylan Wald, Rohit H. Chintala, Olga A. Doronina, Hariswaran Sitaraman, Ethan Young, Ryan King, Jibonananda Sanyal, Marc Day, Ross E. Larsen · Computing in Science & Engineering · 2025
Adaptive computing is an application-agnostic outer-loop framework to strategically deploy simulations and experiments to guide decision making for scale-up analysis. Resources are allocated over successive batches, which makes the allocation adaptive to some objective, such as optimization or model training. The framework enables the characterization and management of uncertainties associated with predictive models of complex systems when scale-up questions lead to significant model extrapolation. A key advancement of this framework is its integration of multifidelity surrogate modeling, uncertainty management, and automated orchestration of various computing and experimentation resources into a single integrated software package. This enables efficient multifidelity modeling across multiple computing resources by incorporating real-world constraints, such as relative queue times and throughput on individual machines into the multifidelity sampling decision. We discuss applications of this framework to problems in the renewable energy space, including biofuels production, material synthesis, perovskite crystal growth, and building electrical loads.