Materials engineering is a key link in the product development process. Yet engineers are often dependent on incomplete databases or third parties to supply the data, delaying the development process. Where many industries are already leveraging their databases with advanced Data Science and Artificial Intelligence (DS/AI) technologies, the CAE industry has still to develop tools to make their databases work for them.

Both the increasing use of novel materials and the expansion of simulation capabilities are generating an unprecedented demand for high quality material data. With new sustainable materials and hybrid material concepts entering the market, a full material database is required for predictive simulations to mitigate the risk of product failures.

As depicted in Figure 1, the classic approach for generating material data fails to provide answers within the given available resources. Costly experimental campaigns and tedious post-processing of raw experimental data is executed by dedicated human resources. This process is not suitable for today’s business pace.

This article will introduce a highly innovative yet pragmatic solution to accelerate the product development process by enriching sparse material databases. The presented solutions leverage the power of Data Science and Artificial Intelligence(DS/AI) technologies in the framework of material data and Integrated Computational Materials Engineering (ICME). The approach to enrich material databases is demonstrated using practical examples.