WaterBench-Iowa: a large-scale benchmark dataset for data-driven streamflow forecasting

Demir, Ibrahim; Xiang, Zhongrun; Demiray, Bekir; Sit, Muhammed

doi:https://doi.org/10.5194/essd-14-5605-2022

Articles | Volume 14, issue 12

https://doi.org/10.5194/essd-14-5605-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Benchmark datasets and machine learning algorithms for Earth...

https://doi.org/10.5194/essd-14-5605-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 14, issue 12

Data description paper

|

20 Dec 2022

Data description paper |

| 20 Dec 2022

WaterBench-Iowa: a large-scale benchmark dataset for data-driven streamflow forecasting

Ibrahim Demir, Zhongrun Xiang, Bekir Demiray, and Muhammed Sit

Data sets

WaterBench-Iowa Ibrahim Demir, Zhongrun Xiang, Bekir Demiray, and Muhammed Sit https://doi.org/10.5281/zenodo.7087806

WaterBench Ibrahim Demir, Zhongrun Xiang, Bekir Demiray, and Muhammed Sit https://www.github.com/uihilab/WaterBench

Model code and software

WaterBench-Iowa Ibrahim Demir, Zhongrun Xiang, Bekir Demiray, and Muhammed Sit https://doi.org/10.5281/zenodo.7087806

Short summary

We provide a large benchmark dataset, WaterBench-Iowa, with valuable features for hydrological modeling. This dataset is designed to support cutting-edge deep learning studies for a more accurate streamflow forecast model. We also propose a modeling task for comparative model studies and provide sample models with codes and results as the benchmark for reference. This makes up for the lack of benchmarks in earth science research.