This $1.02 million National Science Foundation Project Grant, funded under the Engineering program (CFDA 47.041), supports the development of computation-informed deep learning approaches to enable real-time prognosis of melt pool dynamics for additive manufacturing. Over the three-year period from July 2022 to June 2025, the awardee, Rutgers University, will create an integrated model using computational fluid dynamics simulations and deep learning to predict melt pool overheating during metal 3D printing. Key activities include developing simulation data to augment limited real-world datasets, building cyberinfrastructure for data integration and model deployment, and creating semi-supervised deep learning techniques optimized for small training data. The outcomes aim to provide transparency lacking in pure data-driven methods, reduce model training time, and establish an online testbed for additive manufacturing researchers. The grant reflects NSF's mission to advance engineering innovation and supports interdisciplinary workforce development.