Closed lucpaoli closed 10 months ago
Update to this issue: Try training on published generated PCSAFT parameters from transformer paper, then swap out final MLP layer + SAFT head for SAFTVRMie & fine-tune on experimental / GERG data
The PCSAFT parameters in the ETH paper probably aren't to be taken as gospel. Polar methane.
This is a bad idea. Closing the issue.
Advantage:
Perfect case-study! Train to predict SAFT VR Mie parameters for C1-C10, then see if it can continue to learn on dataset including isobutane, isopentane