Artificial Intelligence for Robust Engineering and Science (AIRES) is the process of designing, building, and controlling systems to avoid or mitigate failures.  The introductory AIRES workshop in January 2020 explored these foundations while the second AIRES workshop in January 2021 focused on the foundations of AI for constructing, deploying, and assuring the robustness of digital twins.  The third AIRES workshop to be held on April 26-28, 2022 will build on the successes of the first two workshops in this series and explore and develop the foundations of AI in knowledge-informed modeling and prediction, deployment considerations, and related topics. The three thrusts for the workshop are: Knowledge-informed AI for robust digital models; Assurance for robustness; and, Co-design Ecosystems to address practical challenges when using digital twins.