Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

MM: Fachverband Metall- und Materialphysik

MM 3: Data-driven Materials Science: Big Data and Worksflows

Montag, 17. März 2025, 10:15–13:00, H10

Machine Learning, Potential Development

	10:15	MM 3.1	Benchmarking DFT Functionals at Finite Temperature with ASSYST and MLIPs — •Marvin Poul and Jörg Neugebauer
	10:30	MM 3.2	Assessing the role of physical constraints in machine learning potentials — •Marcel F. Langer, Sergey N. Pozdnyakov, Filippo Bigi, and Michele Ceriotti
	10:45	MM 3.3	Fast and flexible range-separated models for atomistic machine learning — •Philip Loche, Marcel F. Langer, and Michele Ceriotti
	11:00	MM 3.4	Beyond Numerical Hessians: Applications for Higher Order Derivatives in Machine Learning Interatomic Potentials — •Nils Gönnheimer, Karsten Reuter, and Johannes T. Margraf
	11:15	MM 3.5	Diversity-Driven Active Learning of Interatomic Potentials for Reaction Network Exploration — •Francesco Cannizzaro, King Chun Lai, Patricia Poths, Sebastian Matera, Vanessa J. Bukas, and Karsten Reuter
	11:30		15 min. break
	11:45	MM 3.6	Accelerating Materials Exploration with Active Machine Learning: Integrating SISSO with FHI-aims — Yi Yao, Lucas Foppa, Akhil Sugathan Nair, Andrei Sobolev, •Konstantin Lion, Sebastian Kokott, and Matthias Scheffler
	12:00	MM 3.7	Data-driven design of mechanically hard soft magnetic high-entropy alloys — •Mian Dai, Yixuan Zhang, Xiaoqing Li, Stephan Schönecker, Liuliu Han, Ruiwen Xie, Chen Shen, and Hongbin Zhang
	12:15	MM 3.8	Autonomous optimization of coin-cell batteries and thin-film growth — •Edan Bainglass, Peter Kraus, Francisco Ramirez, Enea Svaluto-Ferro, Loris Ercole, Benjamin Kunz, Sebastiaan Huber, Nukorn Plainpan, Nikita Shepelin, Nicola Marzari, Corsin Battaglia, and Giovanni Pizzi
	12:30	MM 3.9	Learning Disorder in Generative Materials Discovery - Bridging Prediction and Experiment — •Konstantin Jakob, Aron Walsh, Karsten Reuter, and Johannes T. Margraf
	12:45	MM 3.10	Materials-Discovery Workflows Guided by Symbolic Regression: Identifying Stable Oxides for Catalytic Applications — •Akhil S. Nair, Lucas Foppa, and Matthias Scheffler