Control of climate and physiography on runoff response behavior through use of catchment classification and machine learning

Shuping Du; Shanhu Jiang; Liliang Ren; Shanshui Yuan; Xiaoli Yang; Yi Liu; Xinglong Gong; Chong-Yu Xu

doi:10.1016/j.scitotenv.2023.166422

Control of climate and physiography on runoff response behavior through use of catchment classification and machine learning

Sci Total Environ. 2023 Nov 15:899:166422. doi: 10.1016/j.scitotenv.2023.166422. Epub 2023 Aug 19.

Authors

Shuping Du¹, Shanhu Jiang², Liliang Ren³, Shanshui Yuan¹, Xiaoli Yang¹, Yi Liu¹, Xinglong Gong⁴, Chong-Yu Xu⁵

Affiliations

¹ College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China.
² College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China; The National Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing 210098, China. Electronic address: hik0216l@hhu.edu.cn.
³ College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China; The National Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing 210098, China.
⁴ School of Water Conservancy & Civil Engineering, Northeast Agricultural University, 150030 Harbin, China.
⁵ Department of Geosciences, University of Oslo, Oslo, Norway.

PMID: 37604375
DOI: 10.1016/j.scitotenv.2023.166422

Abstract

Understanding of runoff response changes (RRC) is essential for water resource management decisions. However, there is a limited understanding of the effects of climate and landscape properties on RRC behavior. This study explored RRC behavior across controls and predictability in 1003 catchments in the contiguous United States (CONUS) using catchment classification and machine learning. Over 1000+ catchments are grouped into ten classes with similar hydrological behavior across CONUS. Indices quantifying RRC were constructed and then predicted within each class of the 10 classes and over the entire1000+ catchments using two machine learning models (random forest and CUBIST) based on 56 indicators of catchment attributes (CA) and 16 flow signatures (FS). This enabled the ranking of the important influential factors on RRC. We found that (i) CA/FS-based clusters followed the ecoregions over CONUS, and the impact of climate on RRC seemed to overlap with physiographic attributes; (ii) CUBIST outperforms the random forest model both within the cluster and over the whole domain, with a mean improvement of 39 % (depending on clusters) within clusters. Runoff sensitivity was better predicted than runoff changes; (iii) FS related to runoff ratio, average, and high flow are the most important for RRC, whereas climate (evaporation and aridity) is a secondary factor; and (iv) RRC patterns are substantial in the dominant factor space. High total changes and catchment characteristic-induced changes occurred mainly at 100°west longitude. The elasticity of climate and catchment characteristics was found to be high in spaces with high evaporation and low runoff ratios and low in spaces with low evaporation and high runoff ratios. Uncertainties existed in the number of catchments between clusters which was verified using a fuzzy clustering algorithm. We recommend that future research that clarifies the impact of uncertainty on hydrological or catchment behavior should be conducted.

Keywords: CUBIST; Climate change; Dominant controls; Hydrological behavior; Random forests; Uncertainty analysis.