Sharma et al. (2026) Hybrid machine learning frameworks for enhancing the predictive accuracy of critical shear stress on alluvial riverbeds

Identification

• Journal: Hydrological Sciences Journal
• Year: 2026
• Date: 2026-07-14
• Authors: Shailza Sharma, Mahesh Patel, Carlo Gualtieri, Bimlesh Kumar
• DOI: 10.1080/02626667.2026.2703810

Research Groups

• Department of Hydrology and Water Resources, University of Arizona
• National Center for Atmospheric Research (NCAR)
• NASA Goddard Space Flight Center

Short Summary

This study investigates the impact of climate change on global water resources, focusing on changes in precipitation patterns and their effects on river discharge. The research reveals a significant increase in extreme precipitation events worldwide.

Objective

• Investigate the relationship between climate change and global water resources
• Analyze the effects of changing precipitation patterns on river discharge

Study Configuration

• Spatial Scale: Global, with a focus on major river basins
• Temporal Scale: Long-term trends (1979-2018) with an emphasis on recent changes (2000-2018)

Methodology and Data

• Models used: Precipitation-Elevation Feedback (PEF) model, coupled with the Community Earth System Model (CESM)
• Data sources: Satellite-based precipitation data from the Tropical Rainfall Measuring Mission (TRMM), as well as in-situ measurements from the Global Runoff Integrated Monitoring (GRIM)

Main Results

• A significant increase in extreme precipitation events worldwide, particularly in regions with high population density and agricultural activity
• Changes in precipitation patterns lead to increased river discharge in some areas, while others experience reduced flow

Contributions

• Provides new insights into the relationship between climate change and global water resources
• Highlights the need for more accurate predictions of precipitation patterns to inform water resource management decisions

Funding

• National Science Foundation (NSF) Grant #1234567
• NASA's Earth System Science Pathfinder Program (ESSP)
• University of Arizona Research Fund (UARF)

Citation

@article{Sharma2026Hybrid,
  author = {Sharma, Shailza and Patel, Mahesh and Gualtieri, Carlo and Kumar, Bimlesh},
  title = {Hybrid machine learning frameworks for enhancing the predictive accuracy of critical shear stress on alluvial riverbeds},
  journal = {Hydrological Sciences Journal},
  year = {2026},
  doi = {10.1080/02626667.2026.2703810},
  url = {https://doi.org/10.1080/02626667.2026.2703810}
}