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

Abstract

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.

Potential of Machine learning techniques compared to MIKE-SHE model for drain flow predictions in tile-drained agricultural areas of Denmark

“…There is a growing interest in the application of ML models in hydrology (Shen, 2018). Most of these studies are aimed at the prediction of the water table depth (Koch et al, 2019;Koch et al, 2021;Schneider et al, 2022), water quality (Erickson et al, 2021;Tesoriero et al, 2015) and stream flow (Bechtold et al, 2014;Kratzert et al, 2019;Kuzmanovski et al, 2015;Mushtaq et al, 2022;Xu et al, 2020;Zia et al, 2015). Few studies addressed the prediction of drain flows (Bjerre et al, 2022;Frederiksen et al, 2023;Kuzmanovski et al, 2015;Motarjemi et al, 2021).…”

“…Two different ML methods are commonly used: decision trees (Bechtold et al, 2014;Bjerre et al, 2022;Erickson et al, 2021;Koch et al, 2019;Koch et al, 2021;Kuzmanovski et al, 2015;Mushtaq et al, 2022;Schneider et al, 2022;Zia et al, 2015) and neural networks (Dai et al, 2023;Lees et al, 2022;Motarjemi et al, 2021;Xu et al, 2020). The performance of these approaches are compared, which in the context of drain flow only has been attempted once previously: Motarjemi et al (2021) https://doi.org/10.5194/egusphere-2023-1872 Preprint.…”