One of the major challenges of implementing additive manufacturing (AM) processes for the purpose of production is the lack of understanding of its underlying process-structure-property relationship. Parts manufactured using AM technologies may be too inconsistent and unreliable to meet the stringent requirements for many industrial applications. The first objective of the present research is to characterize the underlying thermo-physical dynamics of AM process, captured by melt pool signals, and predict porosity during the build. Herein, we propose a novel porosity prediction method based on the temperature distribution of the top surface of the melt pool as the AM part is being built. Advance data analytic and machine learning methods are then used to further analyze the 2D melt pool image streams to identify the patterns of melt pool images and its relationship to porosity. Furthermore, the lack of geometric accuracy of AM parts is a major barrier preventing its use in mission-critical applications. Hence, the second objective of this work is to quantify the geometric deviations of additively manufactured parts from a large data set of laser-scanned coordinates using an unsupervised machine learning approach. The outcomes of this research are: 1) quantifying the link between process conditions and geometric accuracy; and 2) significantly reducing the amount of point cloud data required for characterizing of geometric accuracy.