Machine learning-based prediction of well performance parameters for wellhead choke flow optimization
Ali Akbari, Fatemeh Ghazi, Yousef Kazemzadeh · 2025
Read Machine learning-based prediction of well performance parameters for wellhead choke flow optimization by Ali Akbari, Fatemeh Ghazi, Yousef Kazemzadeh (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-12717276.txt.
Description
Ali Akbari, Fatemeh Ghazi, and Yousef Kazemzadeh pit three machine learning models against a stubborn oilfield estimation problem, in this 2025 study. Wellhead chokes tame the flow from production wells, and predicting what a well will deliver through a given choke setting matters for recovery forecasts and stable operation. Fifty years of physical models and correlations exist, yet none travels well to every field.
The team assembled 182 samples spanning five quantities: liquid rate, wellhead pressure, choke size, sediment and water content, and gas-liquid ratio. On these they trained a convolutional network, a multilayer perceptron, and a radial basis network. The perceptron won clearly, explaining 99.85 percent of variance in training and holding up in validation and testing. The authors pitch machine learning as a field-portable alternative to correlations that were fitted elsewhere and fail quietly at home.
Catalog record
| CREATOR | Ali Akbari, Fatemeh Ghazi, Yousef Kazemzadeh |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |