Publications
2023
Sina Stocker, Hyunwook Jung, Gábor Csányi, C. Franklin Goldsmith, Karsten Reuter, Johannes T. Margraf: Estimating Free Energy Barriers for Heterogeneous Catalytic Reactions with Machine Learning Potentials and Umbrella Integration. In: Journal of Chemical Theory and Computation, 19 (2023). - S. 6796-6804.
doi:10.1021/acs.jctc.3c00541
Johannes T. Margraf, Hyunwook Jung, Christoph Scheurer, Karsten Reuter: Exploring catalytic reaction networks with machine learning. In: Nature Catalysis, 6 (2023). - S. 112-121.
doi:10.1038/s41929-022-00896-y
Hyunwook Jung, Lena Sauerland, Sina Stocker, Karsten Reuter, Johannes T. Margraf: Machine-Learning Driven Global Optimization of Surface Adsorbate Geometries. In: npj Computational Materials, 9 (2023). - .
doi:10.1038/s41524-023-01065-w
Ke Chen, Christian Kunkel, Bingqing Cheng, Karsten Reuter, Johannes T. Margraf: Physics-Inspired Machine Learning of Localized Intensive Properties. In: Chemical Science, 14 (2023). - S. 4913-4922.
doi:10.1039/D3SC00841J
Martin Vondrák, Karsten Reuter, Johannes T. Margraf: q-pac: A Python Package for Machine Learned Charge Equilibration Models. In: The Journal of Chemical Physics, 159 (2023). - .
doi:10.1063/5.0156290
Johannes T. Margraf: Science-Driven Atomistic Machine Learning. In: Angewandte Chemie International Edition, 62 (2023). - .
doi:10.1002/anie.202219170
2022
Simon Wengert, Gábor Csányi, Karsten Reuter, Johannes T. Margraf: A Hybrid Machine Learning Approach for Structure Stability Prediction in Molecular Co-Crystal Screenings. In: Journal of Chemical Theory and Computation, 18 (2022). - S. 4586-4593.
doi:10.1021/acs.jctc.2c00343
Carsten G. Staacke, Simon Wengert, Christian Kunkel, Gábor Csányi, Karsten Reuter, Johannes T. Margraf: Kernel Charge Equilibration: Efficient and Accurate Prediction of Molecular Dipole Moments with a Machine-Learning Enhanced Electron Density Model. In: Machine Learning: Science and Technology, 3 (2022). - .
doi:10.1088/2632-2153/ac568d
Elisabeth Keller, Theodoros Tsatsoulis, Karsten Reuter, Johannes T. Margraf: Regularized Second-Order Correlation Methods for Extended Systems. In: The Journal of Chemical Physics, 156 (2022). - .
doi:10.1063/5.0078119
Ke Chen, Christian Kunkel, Karsten Reuter, Johannes T. Margraf: Reorganization energies of flexible organic molecules as a challenging target for machine learning enhanced virtual screening. In: Digital Discovery, 1 (2022). - S. 147-157.
doi:10.1039/D1DD00038A
Carsten G. Staacke, Tabea Huss, Johannes T. Margraf, Karsten Reuter, Christoph Scheurer: Tackling structural complexity in Li₂S-P₂S₅ Solid-State Electrolytes using Machine Learning Potentials. In: Nanomaterials, 12 (2022). - .
doi:10.3390/nano12172950
Hanna Türk, Elisabetta Landini, Christian Kunkel, Johannes T. Margraf, Karsten Reuter: Assessing Deep Generative Models in Chemical Composition Space. In: Chemistry of Materials, 34 (2022). - S. 9455-9467.
doi:10.1021/acs.chemmater.2c01860
Pierre Kube, Jinhu Dong, Nuria Sánchez Bastardo, Holger Ruland, Robert Schlögl, Johannes T. Margraf, Karsten Reuter, Annette Trunschke: Green synthesis of propylene oxide directly from propane. In: Nature Communications, 13 (2022). - .
doi:10.1038/s41467-022-34967-2
Johannes T. Margraf, Zachary W. Ulissi, Yousung Jung, Karsten Reuter: Heterogeneous Catalysis in Grammar School. In: The Journal of Physical Chemistry C, 126 (2022). - S. 2931-2936.
doi:10.1021/acs.jpcc.1c10285
Sina Stocker, Johannes Gasteiger, Florian Becker, Stephan Günnemann, Johannes T. Margraf: How Robust are Modern Graph Neural Network Potentials in Long and Hot Molecular Dynamics Simulations?. In: Machine Learning: Science and Technology, 3 (2022). - .
doi:10.1088/2632-2153/ac9955
2021
Christian Kunkel, Johannes T. Margraf, Ke Chen, Harald Oberhofer, Karsten Reuter: Active discovery of organic semiconductors. In: Nature Communications, 12 (2021). - .
doi:10.1038/s41467-021-22611-4
Jakob Timmermann, Yonghyuk Lee, Carsten G. Staacke, Johannes T. Margraf, Christoph Scheurer, Karsten Reuter: Data-Efficient Iterative Training of Gaussian Approximation Potentials: Application to Surface Structure Determination of Rutile IrO₂ and RuO₂. In: The Journal of Chemical Physics, 55 (2021). - .
doi:10.1063/5.0071249
Simon Wengert, Gábor Csányi, Karsten Reuter, Johannes T. Margraf: Data-Efficient Machine Learning for Molecular Crystal Structure Prediction. In: Chemical Science, 12 (2021). - S. 4536-4546.
doi:10.1039/D0SC05765G
Carsten G. Staacke, Hendrik H. Heenen, Christoph Scheurer, Gábor Csányi, Karsten Reuter, Johannes T. Margraf: On the role of long-range electrostatics in machine-learned interatomic potentials for complex battery materials. In: ACS Applied Energy Materials, 4 (2021). - S. 12562-12569.
doi:10.1021/acsaem.1c02363
Johannes T. Margraf, Karsten Reuter: Pure non-local machine-learned density functional theory for electron correlation. In: Nature Communications, 12 (2021). - .
doi:10.1038/s41467-020-20471-y
Haobo Li, Yunxia Liu, Ke Chen, Johannes T. Margraf, Youyong Li, Karsten Reuter: Subgroup discovery points to the prominent role of charge transfer in breaking nitrogen scaling relations at single-atom catalysts on VS₂. In: ACS Catalysis, 11 (2021). - S. 7906-7914.
doi:10.1021/acscatal.1c01324
2020
Annika Stuke, Christian Kunkel, Dorothea Golze, Milica Todorović, Johannes T. Margraf, Karsten Reuter, Patrick Rinke, Harald Oberhofer: Atomic structures and orbital energies of 61,489 crystal-forming organic molecules. In: Scientific Data, 7 (2020). - .
doi:10.1038/s41597-020-0385-y
Hyunwook Jung, Sina Stocker, Christian Kunkel, Harald Oberhofer, Byungchan Han, Karsten Reuter, Johannes T. Margraf: Size-extensive molecular machine learning with global representations. In: ChemSystemsChem, 2 (2020). - .
doi:10.1002/syst.201900052
Johannes T. Margraf, Matthias Hennemann, Timothy Clark: EMPIRE: A highly parallel semiempirical molecular orbital program: 3: Born-Oppenheimer molecular dynamics. In: Journal of Molecular Modeling, 26 (2020). - .
doi:10.1007/s00894-020-4293-z
J. Klicpera, S. Giri, Johannes T. Margraf, S. Günnemann: Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules. - (Paper), Veranstaltung: Workshop on Machine Learning for Molecules, NeurIPS 2020, .
Chiara Panosetti, Artur Engelmann, Lydia Nemec, Karsten Reuter, Johannes T. Margraf: Learning to Use the Force: Fitting Repulsive Potentials in Density-Functional Tight-Binding with Gaussian Process Regression. In: Journal of Chemical Theory and Computation, 16 (2020). - S. 2181-2191.
doi:10.1021/acs.jctc.9b00975
Sina Stocker, Gábor Csányi, Karsten Reuter, Johannes T. Margraf: Machine learning in chemical reaction space. In: Nature Communications, 11 (2020). - .
doi:10.1038/s41467-020-19267-x
Benjamin G. Peyton, Connor Briggs, Ruhee D'Cunha, Johannes T. Margraf, T. Daniel Crawford: Machine-Learning Coupled Cluster Properties through a Density Tensor Representation. In: The Journal of Physical Chemistry A, 124 (2020). - S. 4861-4871.
doi:10.1021/acs.jpca.0c02804
Bingqing Cheng, Ryan-Rhys Griffiths, Simon Wengert, Christian Kunkel, Tamas Stenczel, Bonan Zhu, Volker L. Deringer, Noam Bernstein, Johannes T. Margraf, Karsten Reuter, Gábor Csányi: Mapping Materials and Molecules. In: Accounts of Chemical Research, 53 (2020). - S. 1981-1991.
doi:10.1021/acs.accounts.0c00403
2019
Christian Kunkel, Christoph Schober, Johannes T. Margraf, Karsten Reuter, Harald Oberhofer: Finding the right bricks for molecular legos : A data mining approach to organic semiconductor design. In: Chemistry of Materials, 31 (2019). - S. 969-978.
doi:10.1021/acs.chemmater.8b04436
Alejandro Cadranel, Johannes T. Margraf, Volker Strauss, Timothy Clark, Dirk M. Guldi: Carbon Nanodots for Charge-Transfer Processes. In: Accounts of Chemical Research, 52 (2019). - S. 955-963.
doi:10.1021/acs.accounts.8b00673
Albert Bruix, Johannes T. Margraf, Mie Andersen, Karsten Reuter: First-principles-based multiscale modelling of heterogeneous catalysis. In: Nature Catalysis, 2 (2019). - S. 659-670.
doi:10.1038/s41929-019-0298-3
Johannes T. Margraf, Karsten Reuter: Systematic Enumeration of Elementary Reaction Steps in Surface Catalysis. In: ACS Omega, 4 (2019). - S. 3370-3379.
doi:10.1021/acsomega.8b03200
Johannes T. Margraf, Christian Kunkel, Karsten Reuter: Towards Density Functional Approximations from Coupled Cluster Correlation Energy Densities. In: The Journal of Chemical Physics, 150 (2019). - .
doi:10.1063/1.5094788
Duminda S. Ranasinghe, Johannes T. Margraf, Ajith Perera, Rodney J. Bartlett: Vertical Valence Ionization Potential Benchmarks from Equation-of-Motion Coupled Cluster Theory and QTP Functionals. In: The Journal of Chemical Physics, 150 (2019). - .
doi:10.1063/1.5084728
Johannes T. Margraf, Pavlo O. Dral: What is semiempirical molecular orbital theory approximating?. In: Journal of Molecular Modeling, 25 (2019). - .
doi:10.1007/s00894-019-4005-8