The complexity of additive manufacturing processes is extremely demanding and timeconsuming for conventional numerical methods. This may hinder their application within control applications or engineering design loops, where multiple evaluations of a specific model are required, e.g. in the context of process and component optimization. Recent advances in machine learning demonstrate that reliable empirical approaches can increasingly be obtained from Big Data. While a data-driven ansatz is - once trained - fast at prediction, the generation of Big Data in additive manufacturing requires complex, expensive sensor technology. At high speeds and thermal gradients, however, it is sometimes simply not possible to reliably generate certain data even with the best sensor technology at hand. Moreover, certain process characteristics are hidden to the observer and can only be quantified using destructive testing methods. This session deals with joint physics and data-driven approaches in the context of AM simulation. Applications may be real-time simulation, process-structure-property linkage, automated calibration and optimization, model management, ... with the ultimate goal of creating digital twins for additive manufacturing.