Machine Learning has become more important for materials engineering in the last decade. Globally, automated machine learning (AutoML) is growing in popularity with the increasing demand for data analysis solutions. Yet, it is not frequently used for small tabular data. Comparisons and benchmarks already exist to assess the qualities of AutoML tools in general, but none of them elaborates on the surrounding conditions of materials engineers working with experimental data: small datasets with less than 1000 samples. This benchmark addresses these conditions and draws special attention to the overall competitiveness with manual data analysis. Four representative AutoML frameworks are used to evaluate twelve domain-specific datasets to provide orientation on the promises of AutoML in the field of materials engineering. Performance, robustness and usability are discussed in particular. The results lead to two main conclusions: First, AutoML is highly competitive with manual model optimization, even with little training time. Second, the data sampling for train and test data is of crucial importance for reliable results.

Data-driven methods based on artificial intelligence (AI) are powerful yet flexible tools for gathering knowledge and automating complex tasks in many areas of science and practice. Despite the rapid development of the field, the existing potential of AI methods to solve recent industrial, corporate and social challenges has not yet been fully exploited. Research shows the insufficient practicality of AI in domain-specific contexts as one of the main application hurdles. Focusing on industrial demands, this publication introduces a new paradigm in terms of applicability of AI methods, called Usable AI (UAI). Aspects of easily accessible, domain-specific AI methods are derived, which address essential user-oriented AI services within the UAI paradigm: usability, suitability, integrability and interoperability. The relevance of UAI is clarified by describing challenges, hurdles and peculiarities of AI applications in the production area, whereby the following user roles have been abstracted: developers of cyber–physical production systems (CPPS), developers of processes and operators of processes. The analysis shows that target artifacts, motivation, knowledge horizon and challenges differ for the user roles. Therefore, UAI shall enable domain- and user-role-specific adaptation of affordances accompanied by adaptive support of vertical and horizontal integration across the domains and user roles.

Machine learning has become increasingly important in materials design, yet traditional single-task learning (STL) models fail to fully exploit the potential of available data in scenarios involving multiple targets and incomplete datasets. While STL models overlook the inherent correlations between target properties, this study showcases how multi-task learning (MTL) effectively leverages these correlations. Therefore, the performance of MTL methods compared to STL is evaluated across five datasets, covering twelve prediction tasks and incorporating different types and levels of data sparsity. Our findings reveal that MTL significantly outperforms STL, particularly in sparse data scenarios, with up to 15% prediction improvements across all tasks. Moreover, MTL methods utilizing regressor chains with automated machine learning tools achieve superior performance compared to those based on neural networks, with minimal training effort required. This work advances data efficiency in data-driven materials design, establishing MTL as a potent tool for simultaneous learning and predicting multiple material properties.