Berlin 2024 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

MM: Fachverband Metall- und Materialphysik

MM 11: Data Driven Material Science: Big Data and Workflows II

MM 11.3: Talk

Monday, March 18, 2024, 16:15–16:30, C 243

Multi-Objective Optimization of Subgroups for the Discovery of Exceptional Materials — •Lucas Foppa and Matthias Scheffler — The NOMAD Laboratory at the FHI of the MPG and IRIS-Adlershof of the HU Berlin, Germany

Artificial intelligence (AI) can accelerate the design of materials by identifying correlations and complex patterns in data. However, AI methods commonly attempt to describe the entire, practically infinite materials space with a single model, whereas different mechanisms typically govern the materials behaviors in different regions of materials space. The subgroup-discovery (SGD) approach identifies local rules describing exceptional subsets of data with respect to a given target of interest. Thus, SGD can focus on mechanisms leading to exceptional performance.[1] However, the identification of appropriate SG rules requires a careful consideration of the generality-exceptionality tradeoff. Here, we analyse the tradeoff between exceptionality and generality of rules based on a Pareto front of SGD solutions.[2]

[1] B.R. Goldsmith, et al., New. J. Phys. 19, 013031 (2017).

[2] L. Foppa and M. Scheffler, arXiv.2311.10381 (2023).

Keywords: Artificial Intelligence; Materials Discovery; Subgroup Discovery