Data-Efficient Chemical Machine Learning

Margraf Group

Welcome to the website of the chemical machine learning group at the FHI theory department!

We use machine learning (ML) to understand and predict chemical phenomena, such as the nature of complex reaction networks or the properties of new molecules and materials. A major driver of our work is the desire to build accurate, data-efficient models which do not require enourmous reference datasets for training. This is because we want to be able to apply our methods to any problem of chemical interest, not just to those problems for which "big data" happens to be available. To achieve this, we aim to incorporate as much physics as possible into our methods, e.g. by enforcing size-extensivity or a physical description of long-range interactions. This allows performing accurate chemical simulations at unprecedented scales, e.g. to sample large phase spaces or find new functional molecules in chemical space.

The second focus of the group lies in electronic structure theory. Here we are interested in the intersection of wavefunction and density functional methods, with the goal of developing robust and accurate methods that can overcome the large computational costs of the former and the self-interaction problems of the latter. We are also keen on combining ML and electronic structure theory, closing the loop to data-efficient, physics-based ML. A recent example of this is our work on non-local ML-based density functional theory.

Selected Publications

Selected recent publications are listed below (a full list can be found under Publications):

Green synthesis of propylene oxide directly from propane, P. Kube, et al., Nat. Commun. (2022).

Assessing Deep Generative Models in Chemical Composition Space, H. Türk, et al., Chem. Mater. (2022)

A Hybrid Machine Learning Approach for Structure Stability Prediction in Molecular Co-Crystal Screenings, S. Wengert, G. Csányi, K. Reuter, and J. T. Margraf, J. Chem. Theo. Comput. (2022)

How Robust are Modern Graph Neural Network Potentials in Long and Hot Molecular Dynamics Simulations?, S. Stocker, J. Gasteiger, F. Becker, S. Günnemann, and J.T. Margraf, MLST (2022)

Kernel Charge Equilibration: Efficient and Accurate Prediction of Molecular Dipole Moments with a Machine-Learning Enhanced Electron Density Model, C. Staacke, et al., MLST (2022)

Heterogeneous Catalysis in Grammar School, J. T. Margraf, Z. Ulissi, Y. Jung, and K. Reuter, J. Phys. Chem. C (2022)

Regularized second-order correlation methods for extended systems, E. Keller, T. Tsatsoulis, K. Reuter, and J. T. Margraf, J Chem. Phys. (2022)

On the role of long-range electrostatics in machine-learned interatomic potentials for complex battery materials, C. G. Staacke, et al., ACS Appl. Energy Mater. (2021)

Data-Efficient Machine Learning for Molecular Crystal Structure Prediction, S. Wengert, G. Csányi, K. Reuter, and J. T. Margraf, Chem. Sci. (2021)

Pure non-local machine-learned density functional theory for electron correlation, J. T. Margraf, and K. Reuter, Nat. Commun. (2021)

Machine learning in chemical reaction space, S. Stocker, G. Csányi, K. Reuter, and J. T. Margraf, Nat. Commun. (2020)

Size-Extensive Molecular Machine Learning with Global Representations, H. Jung, et al., ChemSystemsChem (2020)

Systematic Enumeration of Elementary Reaction Steps in Surface Catalysis, J. T. Margraf, and K Reuter, ACS Omega (2019)

Making the Coupled Cluster Correlation Energy Machine-Learnable, J. T. Margraf, and K. Reuter, J. Phys. Chem. A (2018)