02 Sep 2022
02 Sep 2022
Status: this preprint is currently under review for the journal HESS.

Hydrologic Interpretation of Machine Learning Models for 10-daily streamflow simulation in Climate sensitive Upper Indus Catchments

Haris Mushtaq1,2, Taimoor Akhtar3, Muhammad Zia-ur-Rahman Hashmi1, and Amjad Masood1 Haris Mushtaq et al.
  • 1Global Change Impact Studies Centre (GCISC), Islamabad, Pakistan
  • 2Weather and Climate Services Limited, Islamabad, Pakistan
  • 3School of Engineering, University of Guelph, ON, Canada

Abstract. Machine learning for hydrologic modeling has seen significant development and has been suggested as a valuable augmentation to physical hydrological modeling, especially in data scarce catchments. In Pakistan, surface water flows predominantly originate from the transboundary Upper Indus sub-catchments of Chenab, Jhelum, Indus and Kabul rivers. These are high elevation data scarce catchments and generated streamflows are highly seasonal and prone to climate change. Given the catchment characteristics, there is utmost need to develop machine learning models that are hydrologically robust. Thus, the current study besides evaluating the potential of three machine learning models for streamflow simulation also focused on the hydrologic interpretation of machine learning models using SHapley Additive exPlananations(SHAP).XGBOOST, RandomForest and Classification and Regression Trees(CART) were evaluated. All of these models performed well and range of R 2 and Nash Efficiency for all three models lies between 0.65 to 0.90. Our study’s most crucial contribution is SHapley Additive exPlananations (SHAP) method which gives extensive insights into the influence of each variable on simulated streamflow. SHAP analysis highlighted the significance of minimum temperature in high elevation zones for both Indus and Chenab catchment where streamflows are dominated by snow and glacier melt. We strongly believe that the findings of this study will promote the use of SHAP analysis for streamflow forecasting in data scarce and high elevation catchments in Pakistan.

Haris Mushtaq et al.

Status: open (until 30 Oct 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Haris Mushtaq et al.

Haris Mushtaq et al.


Total article views: 389 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
314 72 3 389 1 0
  • HTML: 314
  • PDF: 72
  • XML: 3
  • Total: 389
  • BibTeX: 1
  • EndNote: 0
Views and downloads (calculated since 02 Sep 2022)
Cumulative views and downloads (calculated since 02 Sep 2022)

Viewed (geographical distribution)

Total article views: 324 (including HTML, PDF, and XML) Thereof 324 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 28 Sep 2022
Short summary
The study examined ML models for data-driven rainfall–runoff modeling for their capacity of streamflow simulation in four highly seasonal and data-scarce catchments. The SHAP method employed here gives extensive insights into the influence of each variable on simulated streamflow. Our results show that SHAP analysis helps in developing hydrological interpretations of machine learning models and promote its use for streamflow forecasting in data scarce and high elevation catchments.