Publications of Johannes Margraf

Staacke, C.; Wengert, S.; Kunkel, C.; Csányi, G.; Reuter, K.; Margraf, J.: Kernel charge equilibration: efficient and accurate prediction of molecular dipole moments with a machine-learning enhanced electron density model. Machine Learning: Science and Technology 3 (1), 015032 (2022)

Stocker, S.; Gasteiger, J.; Becker, F.; Günnemann, S.; Margraf, J.: How robust are modern graph neural network potentials in long and hot molecular dynamics simulations? Machine Learning: Science and Technology 3 (4), 045010 (2022)

Türk, H.; Landini, E.; Kunkel, C.; Margraf, J.; Reuter, K.: Assessing Deep Generative Models in Chemical Composition Space. Chemistry of Materials 34 (21), pp. 9455 - 9467 (2022)

Wengert, S.; Csányi, G.; Reuter, K.; Margraf, J.: A Hybrid Machine Learning Approach for Structure Stability Prediction in Molecular Co-crystal Screenings. Journal of Chemical Theory and Computation 18 (7), pp. 4586 - 4593 (2022)

Li, H.; Liu, Y.; Chen, K.; Margraf, J.; Li, Y.; Reuter, K.: Subgroup Discovery Points to the Prominent Role of Charge Transfer in Breaking Nitrogen Scaling Relations at Single-Atom Catalysts on VS₂. ACS Catalysis 11 (13), pp. 7906 - 7914 (2021)

Staacke, C.; Heenen, H.; Scheurer, C.; Csányi , G.; Reuter, K.; Margraf, J.: On the Role of Long-Range Electrostatics in Machine-Learned Interatomic Potentials for Complex Battery Materials. ACS Applied Energy Materials 4 (11), pp. 12562 - 12569 (2021)

Timmermann, J.; Lee, Y.; Staacke, C.; Margraf, J.; Scheurer, C.; Reuter, K.: Data-Efficient Iterative Training of Gaussian Approximation Potentials: Application to Surface Structure Determination of Rutile IrO₂ and RuO₂. The Journal of Chemical Physics 155 (24), 244107 (2021)

Wengert, S.; Csányi, G.; Reuter, K.; Margraf, J.: Data-efficient machine learning for molecular crystal structure prediction. Chemical Science 12 (12), pp. 4536 - 4546 (2021)

Wengert, S.; Kunkel, C.; Margraf, J.; Reuter, K.: Accelerating molecular materials discovery with machine-learning. In: High-Performance Computing and Data Science in the Max Planck Society, pp. 40 - 41. Max Planck Computing and Data Facility, Garching (2021)

Margraf, J.: Materials Discovery With Foundation Models. Machine Learning in Chemical and Material Sciences, MLCM-25, Online Event (2025)

Margraf, J.: Science Driven Chemical Machine Learning. DPG Spring Meeting of the Condensed Matter Section (SKM), Berlin, Germany (2024)

Margraf, J.: Science Driven Chemical Machine Learning. CICECO Workshop, Artificial Intelligence for Materials Design, Aveiro, Portugal (2024)

Margraf, J.: Science Driven Chemical Machine Learning. 2nd SIMPLAIX Workshop on Machine Learning for Multiscale Molecular Modeling, Online Event (2024)

Margraf, J.: Extrapolation With Chemical Machine Learning. Beilstein Bozen Symposium 2024, Rüdesheim, Germany (2024)

Margraf, J.: Machine Learning in Chemical Reaction Space. CECAM Flagship Workshop, Machine Learning of First Principles Observables, Berlin, Germany (2024)

Margraf, J.: Machine Learning in Electronic Structure Theory. Seminar, Molecular Modeling, University of Cambridge, Cambridge, UK (2024)

Margraf, J.: Extrapolation With Chemical Machine Learning? Seminar, RESOLV Cluster of Excellence, Bochum, Germany (2024)

Margraf, J.: Science-Driven Chemical Machine Learning. MCIC 2023: Materials Science Meets Artificial Intelligence – Advancements in Research and Innovation, Bochum, Germany (2023)

Margraf, J.: Robust and Electrostatics-Aware Machine Learning Potentials. CECAM Psi-k Research Conference, Bridging Length Scales with Machine Learning, Berlin, Germany (2023)

Margraf, J.: Science-Driven Chemical Machine Learning. Colloquium for Theoretical Chemistry, Universität Marburg, Online Event (2023)