DDR MERIT River Geometry Predictions

A dataset of learned streamflow geometries for rivers within the Multi-Error-Removed-Improved-Terrain (MERIT) Hydro DEM based unit basins data set (Lin et al., 2021). The neural network used to generate these outputs used streamflow inputs from dHBV2.0UH (Song et al. 2025) and was trained using the DDR library. References: Lin, P., Pan, M., Wood, E. F., Yamazaki, D., & Allen, G. H. (2021). A new vector-based global river network dataset accounting for variable drainage density. Scientific Data, 8(1), 28. https://doi.org/10.1038/s41597-021-00819-9 Song, Y., Bindas, T., Shen, C., Ji, H., Knoben, W. J. M., Lonzarich, L., et al. (2025). High-resolution national-scale water modeling is enhanced by multiscale differentiable physics-informed machine learning. Water Resources Research, 61, e2024WR038928. https://doi.org/10.1029/2024WR038928