Jigar’s doctoral research involves the use of data management practices to help improve the usability of machine learning in L-PBF applications, particularly surface roughness. His research involves the design, development and deployment of a database that is scalable to store and manage the vast amounts of data generated throughout the L-PBF life cycle. The database houses data collected throughout the L-PBF lifecycle, such as build preparation data, sensor data and characterization data. This database in then integrated with a machine learning workflow to generate more generalized predictions of L-PBF surface quality. A potential application of this work is a synthetic surface generator that applies roughness texture on ideal CAD profiles.