MLThermoProperties.jl

Appearance

References ​

  1. T. Specht, M. Nagda, S. Fellenz, S. Mandt, H. Hasse and F. Jirasek. HANNA: hard-constraint neural network for consistent activity coefficient prediction. Chemical Science 15, 19777–19786 (2024). Accessed on Nov 25, 2024.

  2. M. Hoffmann, T. Specht, Q. Göttl, J. Burger, S. Mandt, H. Hasse and F. Jirasek. Thermodynamically consistent machine learning model for excess Gibbs energy (Feb 2026). Accessed on Mar 12, 2026, arXiv:2509.06484 [cs].

  3. N. Hayer, T. Wendel, S. Mandt, H. Hasse and F. Jirasek. Advancing thermodynamic group-contribution methods by machine learning: UNIFAC 2.0. Chemical Engineering Journal 504, 158667 (2025). Accessed on Jan 17, 2025.

  4. N. Hayer, H. Hasse and F. Jirasek. Modified UNIFAC 2.0-A Group-Contribution Method Completed with Machine Learning. Industrial & Engineering Chemistry Research 64, 10304–10313 (2025). Accessed on Oct 7, 2025.

  5. M. Hoffmann, H. Hasse and F. Jirasek. GRAPPA—A hybrid graph neural network for predicting pure component vapor pressures. Chemical Engineering Journal Advances 22, 100750 (2025). Accessed on Oct 7, 2025.

  6. J. Wagner, Z. Romero, K. Münnemann, S. Schmitt, T. Specht, H. Hasse and F. Jirasek. Hybrid Machine Learning for Enhanced Prediction of Diffusion Coefficients in Liquids (Mar 2026). Accessed on Mar 4, 2026.