Search Results

Machine learning (ML) has achieved undeniable success in computational mechanics, an ever-growing discipline that impacts all areas of engineering, from structural and fluid dynamics to solid mechanics and vehicle simulation. Computational mechanics uses numerical models and time- and resource-consuming simulations to reproduce physical phenomena, usually with the goal of optimizing the parameter configuration of the model with respect to the desired properties of the system. ML algorithms enable the construction of surrogate models that approximate the outcome of the simulations, allowing faster identification of well-performing configurations. However, determining the best ML approach for a given task is not straightforward and depends on human experts. Automated machine learning (AutoML) aims to reduce the need for experts to obtain effective ML pipelines. It provides off-the-shelf solutions that can be used without prior knowledge of ML, allowing engineers to spend more time on domain-specific tasks. AutoML is underutilized in computational mechanics; there is almost no communication between the two communities, and engineers spend unnecessary effort selecting and configuring ML algorithms. Our Dagstuhl Seminar aimed to (i) raise awareness of AutoML in the computational mechanics community, (ii) discover strengths and challenges for applying AutoML in practice, and (iii) create a bilateral exchange so that researchers can mutually benefit from their complementary goals and needs.