Interatomic machine learning potentials for energy materials
In our group we develop machine-learned interatomic force field potentials for materials that are at the heart of energy conversion processes in battery technology and catalysis.
Battery systems and (electro)catalysis applications are key technologies for the efficient storage of renewable energy. Many of the major challenges still limiting these technologies arise at interfaces which are present in practical devices and are currently very poorly understood. These interfaces are inherently complex and their simulation typically requires large computational models and exhaustive sampling for a realistic representation. Frequently employed computational methods like Density Functional Theory (DFT) or empirical force fields are inappropriate for their treatment since computational cost is prohibitive or accuracy insufficient. In contrast, machine learned force field potentials (ML-FF) offer an alternative route forward as they show great promise of providing both sufficient accuracy and efficiency - thus filling an important application gap.
In our group, we develop strategies to train reliable ML-FF which can capture complex chemical spaces and reactive chemistry. The target ML-FF are intentionally designed to be as general as possible and go beyond single-purpose acceleration schemes where a ML-FF is trained to replace e.g. DFT in a specific task. A major part of our methodological work includes active learning and uncertainty quantification as well as the incorporation of long-range interactions. The development of general-purpose workflows and concepts to "automatically" obtain potentials with limited user input is a long-term goal. We develop and adapt our efforts alongside the investigation of technologically relevant systems that would be otherwise inaccessible (i.e. with DFT), such as Li-Sulfur battery chemistry, deactivation processes of oxygen evolution (OER) catalysts and graphene synthesis.