Nathan’s research focuses on applying machine learning and materials informatics to problems in manufacturing. As part of the ADAPT Center, he works with and studies a wide range of additive manufacturing (AM) technologies, from selective laser melting to electron beam free-form fabrication. The ADAPT Center applies machine learning approaches to discover the process-property relationships inherent in AM technologies. Since AM is a burgeoning technology, the impact that processing conditions have on final part properties is not fully understood. This makes it difficult to consistently manufacture high-quality parts. The ADAPT Center is tackling this problem by using a high-throughput experimentation and computation approach. Test parts are manufactured and characterized, then the data is analyzed with a toolset of machine learning algorithms that elucidate underlying trends and patterns in the process–property relationship. Using this method, the ADAPT Center is optimizing AM processes. The goal is to work toward fully automated manufacturing processes that have in situ quality control. Furthermore, Nathan’s research aims to discover enough about AM process-property relationships to enable multifunctional, highly tailored materials manufacturing.