Su (2026) Stable Stream Temperature Prediction for Different Basins Using Time Series Encoding and Temporal Convolutional Networks: TimENC-TCN model Original Dataset

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

Identification

• Journal: Open MIND
• Year: 2026
• Date: 2026-02-16
• Authors: Lichen Su
• DOI: 10.5281/zenodo.18654574

Research Groups

Not specified in the provided text.

Short Summary

The study develops the TimENC-TCN model, utilizing time series encoding and time-domain convolutional networks, to predict steady-flow water temperature in rivers.

Objective

• To predict steady-flow river water temperatures using a deep learning approach based on time series encoding and time-domain convolutional networks (TimENC-TCN).

Study Configuration

• Spatial Scale: Regional (River stations across the United Kingdom and the United States).
• Temporal Scale: Hourly (based on the NASA POWER project data version used).

Methodology and Data

• Models used: TimENC-TCN (Time Series Encoding and Time-Domain Convolutional Networks).
• Data sources:
  • UK: Environment Agency (hydrology), Met Office (climate).
  • USA: United States Geological Survey (USGS, hydrology), National Oceanic and Atmospheric Administration (NOAA, climate), and NASA Langley Research Center (POWER project, air temperature).

Main Results

Not provided in the source text.

Contributions

Not provided in the source text.

Funding

• NASA Earth Science Division (funding for the Prediction Of Worldwide Energy Resources - POWER project).

Citation

@article{Su2026Stable,
  author = {Su, Lichen},
  title = {Stable Stream Temperature Prediction for Different Basins Using Time Series Encoding and Temporal Convolutional Networks: TimENC-TCN model Original Dataset},
  journal = {Open MIND},
  year = {2026},
  doi = {10.5281/zenodo.18654574},
  url = {https://doi.org/10.5281/zenodo.18654574}
}