Description

This opportunity from the DARPA Defense Sciences Office seeks innovative proposals for the data-informed development of generalizable models and principles for aeronautical design and the optimal control of turbulent systems. The goal is to enable revolutionary, not incremental, advances in science, devices, or systems related to turbulence and aeronautical design. The program, titled AutoDIDACTS, focuses on leveraging precision experimental data and advanced data-informed techniques (including AI/ML) to discover new macroscale design principles and surrogate models that are accurate, predictive, and generalizable across a wide range of conditions.

Research teams are expected to combine expertise in experimental simulators of turbulent flows, data-driven modeling, and aeronautical design. The program is structured in two phases: Phase I (24 months) centers on developing and validating new data-informed models using precision experimental data, while Phase II (24 months, to be solicited separately) will address specific challenge problems in aeronautics and turbulence control.

Proposals must address all goals of Phase I, including rigorous uncertainty quantification, interpretability of models, and demonstration of generalizability. Research that only yields evolutionary improvements to the current state of practice is specifically excluded.