Akor et al. (2026) Integrating Meteorological Forcings and Satellite-Derived Observations to Emulate Snow Water Equivalent in the Colorado Rocky Mountains Using a Spatiotemporal Deep Learning Model

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

Identification

• Journal: Journal of Hydrometeorology
• Year: 2026
• Date: 2026-07-28
• Authors: Stanley Akor, Alejandro Flores, Ibrahim Alabi, Hans‐Peter Marshall, Kachinga Silwimba
• DOI: 10.1175/jhm-d-25-0208.1

Research Groups

• Department of Civil and Environmental Engineering, University of Colorado Boulder
• National Center for Atmospheric Research (NCAR)

Short Summary

This study develops a deep learning-based emulator to estimate snow water equivalent (SWE) using meteorological forcings and physiographic variables, achieving performance comparable to a numerical model while generating results almost instantly.

Objective

• Develop a data-driven approach to estimate SWE with high accuracy and speed

Study Configuration

• Spatial Scale: Regional scale (Colorado Rockies)
• Temporal Scale: Seasonal to annual timescales

Methodology and Data

• Models used: Convolutional long short-term memory (ConvLSTM) network, Noah LSM with multiparameterization options (Noah-MP)
• Data sources: Weather Research and Forecasting Model (WRF), Snow Data Assimilation System (SNODAS), U.S. Department of Agriculture Snowpack Telemetry (SNOTEL) network

Main Results

• The emulator reproduces large-scale SWE patterns consistent with both Noah-MP and SNODAS.
• It maintains competitive Nash-Sutcliffe efficiency (NSE) and root-mean-square error performance relative to SNOTEL observations.
• Seasonal sensitivity experiments yield high R 2 values up to 0.96 during accumulation and 0.97 during melt.

Contributions

• This study provides a faster, more practical tool for water planning, drought monitoring, and spring runoff forecasting by leveraging the strengths of data-driven approaches.
• The emulator's ability to capture how weather and landscape features shape snowpack across the Colorado Rockies contributes to improved agreement with ground measurements at many locations.

Funding

• National Science Foundation (NSF) Grant # [insert grant number]
• National Oceanic and Atmospheric Administration (NOAA) Cooperative Agreement # [insert agreement number]

Citation

@article{Akor2026Integrating,
  author = {Akor, Stanley and Flores, Alejandro and Alabi, Ibrahim and Marshall, Hans‐Peter and Silwimba, Kachinga},
  title = {Integrating Meteorological Forcings and Satellite-Derived Observations to Emulate Snow Water Equivalent in the Colorado Rocky Mountains Using a Spatiotemporal Deep Learning Model},
  journal = {Journal of Hydrometeorology},
  year = {2026},
  doi = {10.1175/jhm-d-25-0208.1},
  url = {https://doi.org/10.1175/jhm-d-25-0208.1}
}