Hammond (2026) Model inputs for machine learning models forecasting streamflow drought at gaged and ungaged locations across the conterminous United States

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: USGS DOI Tool Production Environment
• Year: 2026
• Date: 2026-09-14
• Authors: John C. Hammond
• DOI: 10.5066/p137x3ck

Research Groups

• Department of Hydrology, University of Colorado Boulder
• National Center for Atmospheric Research (NCAR)

Short Summary

This dataset provides a comprehensive collection of time series data for machine learning models to predict streamflow drought across the conterminous United States, supporting both gaged model training and ungaged prediction.

Objective

• Investigate the feasibility of using machine learning models to predict streamflow drought in ungauged basins.

Study Configuration

• Spatial Scale: Continental (conterminous United States)
• Temporal Scale: Weekly time series

Methodology and Data

• Models used: Machine learning models for predicting streamflow drought
• Data sources:
  • WaterWatch gridded runoff estimates
  • Existing published datasets for model inputs

Main Results

• A comprehensive dataset of 4,952 feather files containing time series data for machine learning model inputs.
• Weekly time series of streamflow percentiles, meteorology, snow water equivalent, forecast meteorology, estimated water use, soil moisture, and WaterWatch runoff estimates.

Contributions

• Provides a valuable resource for researchers to develop and train machine learning models for predicting streamflow drought in ungauged basins.

Funding

• Not specified

Citation

@article{Hammond2026Model,
  author = {Hammond, John C.},
  title = {Model inputs for machine learning models forecasting streamflow drought at gaged and ungaged locations across the conterminous United States},
  journal = {USGS DOI Tool Production Environment},
  year = {2026},
  doi = {10.5066/p137x3ck},
  url = {https://doi.org/10.5066/p137x3ck}
}