Prediction of solubility of hydrogen in chemicals using QSPR-based machine learning approach: a comparative study
Ali Ebrahimpoor Gorji, Ville Alopaeus · 2026
Read Prediction of solubility of hydrogen in chemicals using QSPR-based machine learning approach: a comparative study by Ali Ebrahimpoor Gorji, Ville Alopaeus (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13421244.txt.
Description
Ali Ebrahimpoor Gorji and Ville Alopaeus compare machine-learning approaches in a 2026 study that predicts how much hydrogen dissolves in different chemicals. How much hydrogen dissolves matters for storage and plant design, since the amount shifts with heat and pressure. Testing each mix by hand is not practical.
Their dataset held 3,761 measurements covering 100 chemicals. Their model used the simplest form of machine learning, a multiple linear regression. It read molecular clues within a structure-property framework. The team also ran internal checks that earlier models had skipped. It predicted well on both training and test portions. They argue that a plain, open model can match far more complex rivals here.
Catalog record
| CREATOR | Ali Ebrahimpoor Gorji, Ville Alopaeus |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |