Computational and data-enabled science has become the third pillar of science, completing theory and experimentation. One simplified way to organize the vast number of approaches in this area is by the specificity of the model and the amounts of data required. This idea is often used to categorize approaches as model-based and data-driven approaches. Model-based approaches calibrate unknown parameters in integral or differential equations derived from first principles using measurement data; a process known as data assimilation. Advances in theory and computation have impacted many applications, e.g., numerical weather prediction, medical applications, and storm surge modeling. Due to the high specificity of the modeling, one often needs only a few measurements to predict reliably. By contrast, data-driven approaches use a fairly generic model (e.g., a neural network) that is trained with larger amounts of data. Their use has been successful in applications in which the relevant first principles are ill-defined, or a consistent model is mathematically and computationally intractable for real problems. Despite achieving impressive results, with some notable exceptions, these models are data greedy and often lack understanding and interpretability. In our projects, the teams will apply, compare, and combine data-driven and model-based approaches to solve real problems.

Models Meet Data