Skip to content
Open access

Future Streamflow Projections in a Semi-Arid Mountain Basin Using Machine Learning and CMIP6 Climate Scenarios: The Case of the Zat River (Morocco)

Aug 2026 · Atmosphere · 0 citations · 53 references

Abstract

Understanding how climate change may alter river discharge in semi-arid regions is essential for sustainable water-resource management. This study assesses future streamflow in the Zat River Basin (High Atlas Mountains, Morocco) using a hybrid framework that combines machine-learning rainfall–runoff modeling, CMIP6 multi-model climate forcing, monthly quantile-mapping post-processing of simulated discharge, and an exploratory temperature-sensitivity assessment. Monthly hydroclimatic observations of precipitation, air temperature, reference evapotranspiration, and discharge were compiled from February 1962 to August 2024. The period 1962–2005 was used for model development, the 2006–2014 window for chronological validation, and the more recent observations for supplementary evaluation of climate-driven simulations. Four algorithms were compared: Gradient Boosting Regressor (GBR), Histogram-based Gradient Boosting Regressor (HGBR), Random Forest (RF), and Multi-Layer Perceptron (MLP). Performance was assessed using NSE, KGE, RMSE, MAE, and R2. GBR provided the best validation performance (NSE = 0.71, KGE = 0.80, and R2 = 0.72). The selected model was then forced with CMIP6 projections under SSP2-4.5 and SSP5-8.5 to simulate streamflow to 2100. Quantile mapping was applied to the simulated discharge, rather than separately to precipitation, temperature, and reference evapotranspiration. The multi-model ensemble indicates a persistent drying tendency: relative to the historical baseline and without an additional temperature-sensitivity adjustment, mean annual discharge is projected to decline by approximately 12.1% under SSP2-4.5 and 27.3% under SSP5-8.5 by 2081–2100. Under an exploratory sensitivity case using a runoff-temperature-sensitivity coefficient of 0.04 °C−1, the projected declines increase to approximately 23.3% and 44.1%, respectively. Episodic high-flow events nevertheless remain possible, suggesting a shift toward lower mean flows combined with persistent hydrological extremes.

Read PDF

Similar papers

Open access Aug 2026

Future Vegetation Dynamics in an Arid Inland River Basin Under CMIP6 Scenarios: Insights from a Machine Learning Framework

Against the backdrop of global warming and the “warming and moistening” trend in northwestern China, arid inland river basins are highly sensitive to climate change, with their vegetation dynamics strongly controlled by upstream snowmelt water supply. The Keriya River Basin, situated on the northern slope of the Kunlun...

Wei-Xiang Sun, Jiayi Zheng, Lin-Wei Guan et al. · 0 citations
Open access Sep 2026

One-month-ahead river discharge forecasting using machine learning and limited hydrometeorological data: the Karatoya-Atrai River basin, Bangladesh

Bangladesh, a riverine country, relies heavily on its intricate network of rivers and water bodies. With over 700 rivers flowing through its landscape, water resources are integral to the nation’s agriculture, transportation, and overall way of life. Effective management of these resources is vital to mitigating the...

K. M. Khan, Md. Nazrul Islam, Bo Wang · 0 citations
Open access Sep 2026

Surface Thermal State, Antecedent Hydroclimate, and Post-Fire Vegetation–Water Response in the Zambezi River Basin: A Multi-Source Environmental Time-Series Analysis

Wildfire in African savannas reflects coupled surface thermal, hydroclimatic, vegetation, and disturbance processes, but basin-scale time-series analyses can overstate mechanisms when temporal dependence and spatial heterogeneity are ignored. We assembled a monthly 2003–2024 multi-source environmental dataset for the Z...

Hunter Lutz, Garrett Uthlaut, Robin Kim et al. · 0 citations
Open access Oct 2026

Coupling Machine Learning with the SWAT Model to Predict Future Runoff and Extreme Hydrological Events Under the Effects of Climate Change and Human Activities: A Socio-Hydrological Attribution Study

Projecting runoff and extreme hydrological events in human-modified basins requires climate, land-use and reported water-consumption forcings to be represented within a single, traceable scenario framework. Here, the Dawen River, the largest tributary of the lower reaches of the Yellow River, was selected as the study...

Shao-Han Xie, Yu-Qi Tian, Yi-Shi Wang et al. · 0 citations
Open access Oct 2026

Future Drought Under Climate Change: A Multi-Model Comparison of SPI and SPEI in the Western Black Sea Basin, Türkiye

Because of the increasing negative effects of drought on sectors such as water resources, the economy and agriculture, there is a strong need to study drought and its projections. Given the importance of studying different scenarios regarding drought and climate change, this study presents an integrated modelling frame...

Muhammed Zakir Keskin, E. Gemici, E. Şişman · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.