All models available on this platform are developed by the Laboratory of Engineering Thermodynamics (LTD) at RPTU Kaiserslautern. All models only require the input of the molecular structure in forms of SMILES. Below is a list of currently available models on this platform with a brief description and a link to the corresponding publication.

UNIFAC 2.0 and modified UNIFAC 2.0

  • Combining machine learning with classical group-contribution
  • Missing parameters predicted with matrix completion
  • Higher prediction accuracy than the original methods
  • UNIFAC 2.0 paper, mod. UNIFAC 2.0 pre-print
image

HANNA - Hard-constraint Neural Network for Consistent Activity Coefficient Prediction

  • Prediction of binary activity coefficients
  • Strict thermodynamic consistency
  • Paper available in Chemical Science
image

GRAPPA - Graph Neural Network for Predicting the Parameters of the Antoine Equation

  • Vapor pressure and boiling point prediction
  • Based on the Antoine equation
  • ln(ps/kPa) = A - B / (C + T/K)
  • Pre-print available on arXiv
image

HANNA + GRAPPA - Prediction of Vapor-Liquid Equilibria

  • Prediction of isothermal and isobaric binary VLE
  • Vapor pressure calculated by GRAPPA
  • Activity coefficients calculated by HANNA
image