Amini, Hossein, Shakeri, Reza, Ghaderi, Narjes, Fakheri, Farshid, Morovati, Khosro, Zahraie, Banafsheh and Ahmadian, Reza  ORCID: https://orcid.org/0000-0003-2665-4734
2026.
Interpretable machine learning for river salinity dynamics in arid basins.
Scientific Reports
16
, 18310.
10.1038/s41598-026-49042-9
|
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (2MB) | Preview |
Abstract
Managing salinity in arid rivers is impeded by sparse monitoring, relying on low-frequency grab samples that miss hydrological event dynamics. Here, interpretable machine learning is applied to a 50-year monthly archive (1968-2018; Discharge, major ions, pH) from three stations on Iran's Karkheh River. Gradient Boosting Regression achieves high predictive skill for Total Dissolved Solids (TDS)/Electrical Conductivity (EC) (test-set R = 0.94/0.97; RMSE = 55 mg L /56 µS cm ), validated via time-aware cross-validation. SHAP-based feature attribution reveals that Na and SO are the strongest contributors to TDS, while Na and Cl dominate EC, consistent with conservative salinity sources under baseflow conditions. A reduced-input decision tree (four predictors) retains R = 0.81-0.87, enabling minimal-sensor monitoring. Flow-regime partitioning and STL (Seasonal-Trend decomposition using Locally estimated scatterplot smoothing)-detrended event composites reveal low-flow salinization and ion-specific post-flood recovery (Cl : 1-2 months; Na : 2-3 months), guiding targeted sampling. This framework extracts predictive power, process associations, and operational guidance from legacy grab-sample archives, scalable to data-limited basins worldwide. [Abstract copyright: © 2026. The Author(s).]
| Item Type: | Article |
|---|---|
| Date Type: | Publication |
| Status: | Published |
| Schools: | Schools > Engineering |
| Publisher: | Nature Research |
| ISSN: | 2045-2322 |
| Date of First Compliant Deposit: | 8 May 2026 |
| Date of Acceptance: | 13 April 2026 |
| Last Modified: | 13 Jul 2026 12:45 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/186878 |
Actions (repository staff only)
 |
Edit Item |
Dimensions
Dimensions