Regionalization in a global hydrologic deep learning model: From physical descriptors to random vectors

@article{https://doi.org/10.1029/2021WR031794,
author = {Li, Xiang and Khandelwal, Ankush and Jia, Xiaowei and Cutler, Kelly and Ghosh, Rahul and Renganathan, Arvind and Xu, Shaoming and Tayal, Kshitij and Nieber, John and Duffy, Christopher and Steinbach, Michael and Kumar, Vipin},
title = {Regionalization in a global hydrologic deep learning model: From physical descriptors to random vectors},
journal = {Water Resources Research},
volume = {n/a},
number = {n/a},
pages = {e2021WR031794},
doi = {https://doi.org/10.1029/2021WR031794},
url = {https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2021WR031794},
eprint = {https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2021WR031794},
note = {e2021WR031794 2021WR031794},
abstract = {Abstract Streamflow prediction is a long-standing hydrologic problem. Development of models for streamflow prediction often requires incorporation of catchment physical descriptors to characterize the associated complex hydrological processes. Across different scales of catchments, these physical descriptors also allow models to extrapolate hydrologic information from one catchment to others, a process referred to as “regionalization”. Recently, in gauged basin scenarios, deep learning models have been shown to achieve state of the art regionalization performance by building a global hydrologic model. These models predict streamflow given catchment physical descriptors and weather forcing data. However, these physical descriptors are by their nature uncertain, sometimes incomplete, or even unavailable in certain cases, which limits the applicability of this approach. In this paper, we show that by assigning a vector of random values as a surrogate for catchment physical descriptors, we can achieve robust regionalization performance under a gauged prediction scenario. Our results show that the deep learning model using our proposed random vector approach achieves a predictive performance comparable to that of the model using actual physical descriptors. The random vector approach yields robust performance under different data sparsity scenarios and deep learning model selections. Furthermore, based on the use of random vectors, high-dimensional characterization improves regionalization performance in gauged basin scenario when physical descriptors are uncertain, or insufficient. This article is protected by copyright. All rights reserved.}
}