Integrating Self-Organizing Maps and Explainable Artificial Intelligence to Unravel Surface Water-Groundwater Hydrochemical Evolution and Drinking-Water Suitability Controls in a Data-Limited Arid Basin

Authors

• Hui Tong, Inner Mongolia Agricultural University
• Ruizhong Gao, Inner Mongolia Agricultural University
• Yinlong Wang, Inner Mongolia Agricultural University
• Xixi Wang, Old Dominion UniversityFollow
• Limin Duan, Inner Mongolia Agricultural University
• Guoqiang Wang, Beijing Normal University

Document Type

Article

Publication Date

2026

DOI

10.1016/j.ejrh.2026.103988

Publication Title

Journal of Hydrology: Regional Studies

Volume

68

Pages

103988 (16 pp.)

Abstract

Study region

The Dahei River Basin, located in the semi-arid northern region of China's Great Bend of the Yellow River.

Study focus

This study integrates hydrochemical characterization, stable hydrogen-oxygen isotopes, Self-Organizing Maps (SOM), the entropy-weighted water quality index (EWQI), and explainable ensemble learning (XGBoost-TreeSHAP) to investigate surface water-groundwater evolutionary patterns and identify key hydrochemical contributors to drinking-water suitability in the Dahei River Basin.

New hydrological insights for the region

Waters in the basin are predominantly weakly alkaline and are characterized by HCO₃^--Ca-Mg and HCO₃^--Na facies, indicating the combined effects of carbonate weathering and cation exchange, with localized contributions from evaporite dissolution and external inputs. SOM reveals a continuous hydrochemical evolution, ranging from lowsalinity recharge waters to mineralized discharge end-members. Stable isotopes indicate seasonally variable surface water-groundwater connectivity, with stronger coupling during the wet season and greater isotopic divergence during the dry season. EWQI results suggest favorable groundwater quality, with approximately 65% of samples classified as excellent to good, showing a distinct spatial gradient from higher quality in the northern mountainous areas to lower quality in the southern plains. XGBoost-TreeSHAP indicates that Cl- and TDS make major contributions to EWQI predictions, whereas NO₃- shows a contribution pattern consistent with localized agricultural influence. Overall, this study provides a regime-resolved and interpretable framework for assessing groundwater suitability in data-limited arid and semi-arid regions.

Rights

© 2026 The Authors.

This is an open access article under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.

Data Availability

Article states: "Data will be made available on request."

ORCID

0000-0003-3455-3124 (Wang)

Original Publication Citation

Tong, H., Gao, R. Z., Wang, Y. L., Wang, X. X., Duan, L. M., & Wang, G. Q. (2026). Integrating self-organizing maps and explainable artificial intelligence to unravel surface water-groundwater hydrochemical evolution and drinking-water suitability controls in a data-limited arid basin. Journal of Hydrology: Regional Studies, 68, Article 103988. https://doi.org/10.1016/j.ejrh.2026.103988 

Repository Citation

Tong, Hui; Gao, Ruizhong; Wang, Yinlong; Wang, Xixi; Duan, Limin; and Wang, Guoqiang, "Integrating Self-Organizing Maps and Explainable Artificial Intelligence to Unravel Surface Water-Groundwater Hydrochemical Evolution and Drinking-Water Suitability Controls in a Data-Limited Arid Basin" (2026). Civil & Environmental Engineering Faculty Publications. 172.
https://digitalcommons.odu.edu/cee_fac_pubs/172