Ensemble machine learning method for δ18O prediction in groundwater
Faten A Mohamed, Mostafa Sadek, Nema Mohamed Kandil · 2026
Read Ensemble machine learning method for δ18O prediction in groundwater by Faten A Mohamed, Mostafa Sadek, Nema Mohamed Kandil (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/PMC13284213.txt.
Description
Machine learning predicts groundwater oxygen-isotope values well only within its data heartland, caution Faten A Mohamed and colleagues in 2026. Isotope readings help trace recharge and salt build-up in dry regions. Sparse sampling in the mid-Nile Valley made model testing valuable.
Three ensemble methods competed on chemistry and location variables together. Random splitting flattered all models, with the forest method on top. Honest spatial testing cut accuracy roughly in half across methods. Longitude and three chemistry measures drove most predictions in the models. Without location, chemistry alone explained about forty percent of variance. Edge samples carried much wider uncertainty.
Catalog record
| CREATOR | Faten A Mohamed, Mostafa Sadek, Nema Mohamed Kandil |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44328 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |