Machine learning-based modeling for precise runoff forecasts in hydrological systems
Ali Aldrees, Bilal Siddiq, Muhammad Faisal Javed · 2026
Read Machine learning-based modeling for precise runoff forecasts in hydrological systems by Ali Aldrees, Bilal Siddiq, Muhammad Faisal Javed (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/pmc-13483116.txt.
Description
Aldrees and team combined machine-learning models with a swarm-based tuning method to forecast daily river runoff, the water flowing from rainfall into streams. Their 2026 study used nine years of rainfall data and tested three base models, each tuned by particle swarm optimization, an approach that mimics flocking birds to search for good settings. Better forecasts help towns prepare for floods and drought.
The tuned gradient-boosting model won, explaining nearly all the variation in daily runoff in the results presented. The tuned boosting variant finished close behind, while the tuned equation-based model lagged further back. All hybrids beat their untuned counterparts. The authors also built a simple software interface so engineers can run the models without coding, and they published an equation version for quick estimates. Aldrees presents the tuned booster as the practical pick for daily forecasting.
Catalog record
| CREATOR | Ali Aldrees, Bilal Siddiq, Muhammad Faisal Javed |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |