TY - JOUR
T1 - Regionalization in a Global Hydrologic Deep Learning Model
T2 - From Physical Descriptors to Random Vectors
AU - Li, Xiang
AU - Khandelwal, Ankush
AU - Jia, Xiaowei
AU - Cutler, Kelly
AU - Ghosh, Rahul
AU - Renganathan, Arvind
AU - Xu, Shaoming
AU - Tayal, Kshitij
AU - Nieber, John
AU - Duffy, Christopher
AU - Steinbach, Michael
AU - Kumar, Vipin
N1 - Publisher Copyright:
© 2022. The Authors.
PY - 2022/8
Y1 - 2022/8
N2 - 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.
AB - 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.
KW - Random vectors
KW - deep learning
KW - physical descriptors
KW - regionalization
KW - streamflow prediction
UR - http://www.scopus.com/inward/record.url?scp=85136873806&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136873806&partnerID=8YFLogxK
U2 - 10.1029/2021WR031794
DO - 10.1029/2021WR031794
M3 - Article
AN - SCOPUS:85136873806
SN - 0043-1397
VL - 58
JO - Water Resources Research
JF - Water Resources Research
IS - 8
M1 - e2021WR031794
ER -