Enterprises are grappling with increasingly vast amounts of data, where data fuels transformative technologies like machine learning and data-driven products. However, amidst this surge, ensuring data quality has become paramount. Data arrives from myriad sources, in varying structures, and at unprecedented speeds. Maintaining data quality is essential for unlocking the potential of data-driven technologies and data-intensive business models, particularly in distributed environments, where data suppliers and consumers operate independently from the data provider.

Numerical simulations in engineering and science are often costly and time-consuming. While machine learning-based surrogate models offer a solution, they typically require large datasets. This project aims to develop adaptive models that can be repurposed for similar tasks, such as new PDE problems, using minimal data. By leveraging sparse data and techniques like transfer learning, meta-learning and few-shot learning, the project will enhance the efficiency and accuracy of these models, reducing the need for large datasets and enabling faster assessments.

As the range of data platforms is rapidly evolving, the goal of this research project is to investigate and prototype upcoming architectures and technologies and to assess their applicability and potentials for industrial enterprises.