Publikationen von Matteo Krüger

Krüger, M.; Galeazzo , T.; Eremets, I.; Schmidt, B.; Pöschl, U.; Shiraiwa, M.; Berkemeier, T.: Improved vapor pressure predictions using group contribution-assisted graph convolutional neural networks (GC²NN). Geoscientific Model Development 18 (20), S. 7357 - 7371 (2025)

Krüger, M.; Mishra, A.; Spichtinger , P.; Pöschl, U.; Berkemeier, T.: A numerical compass for experiment design in chemical kinetics and molecular property estimation. Journal of Cheminformatics 16, 34 (2024) (2024)

Berkemeier, T.; Krüger, M.; Feinberg, A.; Müller, M.; Pöschl, U.; Krieger, U. K.: Accelerating models for multiphase chemical kinetics through machine learning with polynomial chaos expansion and neural networks. Geoscientific Model Development 16 (7), S. 2037 - 2054 (2023)

Krüger, M.; Wilson, J.; Wietzoreck, M.; Bandowe, B. A. M.; Lammel, G.; Schmidt, B.; Pöschl, U.; Berkemeier, T.: Convolutional neural network prediction of molecular properties for aerosol chemistry and health effects. Natural Sciences 2 (2022)

Raj, S. S.; Hrabe de Angelis, I.; Basic, S.; Aardema, H. M.; Slagter, H. A.; Weber, J.; Calleja, M. L.; Krüger, M.; Andreae, M. O.; Dragoneas, A. et al.; Nillius, B.; Walter, D.; Berkemeier, T.; Haug, G. H.; Pöschl, U.; Schiebel, R.; Pöhlker, C.: Exploring aerosol size distributions from polar to tropical zones of the Atlantic Ocean. In EGU General Assembly 2024, Vienna, Austria & Online, EGU24-15400. EGU General Assembly 2024, Vienna, 14. April 2024 - 19. April 2024. (2024)

Krüger, M.; Galeazzo , T.; Eremets, I.; Schmidt, B.; Pöschl, U.; Shiraiwa, M.; Berkemeier, T.: Improved vapor pressure predictions using group contribution-assisted graph convolutional neural networks (GC²NN). EGUsphere (2025)

Krüger, M.; Mishra, A.; Spichtinger , P.; Pöschl, U.; Berkemeier, T.: A kinetic compass for the design of experiments to determine kinetic parameters. Research Square (2023)

Berkemeier, T.; Krüger, M.; Feinberg, A.; Müller, M.; Pöschl, U.; Krieger, U. K.: Accelerating models for multiphase chemical kinetics through machine learning with polynomial chaos expansion and neural networks. EGUsphere (2022)