As an engineering community we have been working towards developing detailed mathematical simulation models which accurately capture the behavior of complex systems. This trend is reinforced by our drive to couple multiscale information which ranges from the atomistic and molecular level to continuum, process and even plant and enterprise levels. At the same time, abundance of data is transforming traditional process systems engineering operations in this “Big Data” era, complementing existing mechanistic models or even enabling the description and analysis of problems for which a model is not available. However, as we move towards this paradigm we create a gap between the current state-of-the-art high-fidelity models, and the models which are used in significant process operations such as design, optimization and control. Our research interests integrate theory from various fields, such as statistics, machine learning, operations research, mathematics and engineering, to solve significant problems which are characterized by abundance in experimental and/or computational data; lack of closed-form numerically stable models; and integration of data and models across scales.