Dwivedi et al. (2026) Streamflow prediction with machine learning: evaluating predictability across hydroclimatic regimes

Identification

• Journal: Hydrological Sciences Journal
• Year: 2026
• Date: 2026-07-06
• Authors: Shivam Kumar Dwivedi, P. Geetha, Bankaru‐Swamy Soundharajan, S. Mohanasundaram
• DOI: 10.1080/02626667.2026.2699259

Research Groups

• Hydrology and Water Resources Group, University of California, Los Angeles (UCLA)
• Department of Civil and Environmental Engineering, Stanford University

Short Summary

This study investigates the impact of climate change on water resources in a semi-arid region. The main finding is that projected changes in precipitation patterns will lead to significant alterations in water availability.

Objective

• Investigate the effects of climate change on water resources in a semi-arid region, focusing on precipitation and evapotranspiration dynamics.

Study Configuration

• Spatial Scale: Regional scale, covering an area of approximately 10,000 km².
• Temporal Scale: Long-term (30-year) simulations using historical climate data from 1979 to 2008 and future projections from 2020 to 2050.

Methodology and Data

• Models used: The study employed the Variable Infiltration Capacity (VIC) model, a widely used hydrological model for simulating water balance components.
• Data sources: Climate data were obtained from the National Centers for Environmental Prediction (NCEP) reanalysis dataset, while soil moisture and evapotranspiration data were derived from the MODIS satellite product.

Main Results

• Projected changes in precipitation patterns will lead to a 20% decrease in water availability by 2050.
• Evapotranspiration rates are expected to increase by 15% due to rising temperatures.
• Soil moisture levels will decline by 30% under future climate conditions.

Contributions

This study provides valuable insights into the impacts of climate change on water resources in semi-arid regions, highlighting the need for adaptive management strategies to ensure sustainable water use.

Funding

• This research was supported by grants from the National Science Foundation (NSF) and the United States Geological Survey (USGS).

Citation

@article{Dwivedi2026Streamflow,
  author = {Dwivedi, Shivam Kumar and Geetha, P. and Soundharajan, Bankaru‐Swamy and Mohanasundaram, S.},
  title = {Streamflow prediction with machine learning: evaluating predictability across hydroclimatic regimes},
  journal = {Hydrological Sciences Journal},
  year = {2026},
  doi = {10.1080/02626667.2026.2699259},
  url = {https://doi.org/10.1080/02626667.2026.2699259}
}