Integrating experimental data and machine learning models for solubility prediction of yellow 23 in supercritical carbon dioxide
Seyed Ali Sajadian, Amir Hossein Sheikhshoaei, Nadia Esfandiari, Adel Noubigh · 2025
Read Integrating experimental data and machine learning models for solubility prediction of yellow 23 in supercritical carbon dioxide by Seyed Ali Sajadian, Amir Hossein Sheikhshoaei, Nadia Esfandiari, Adel Noubigh (2025) 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/pmc-12706848.txt.
Description
Seyed Ali Sajadian and co-authors measure how much of a yellow dye dissolves in carbon dioxide squeezed into a supercritical fluid, then teach machines to predict it. Such fluids dye fabrics without water, but solubility data for this dye did not exist. Their 2025 paper reports the first measurements, across pressures of 12 to 30 megapascals and temperatures from 313 to 343 kelvin.
Four classical formulas were fitted to the data, and the K-J model matched best, erring by about six percent on average. Three machine learning models were trained alongside: a multilayer perceptron, a Gaussian process, and a random forest. All three approximated the measurements well, and the perceptron won with a near-perfect fit score. The authors offer both the raw data and the winning model as design tools for greener dyeing.
Catalog record
| CREATOR | Seyed Ali Sajadian, Amir Hossein Sheikhshoaei, Nadia Esfandiari, Adel Noubigh |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |