Can transfer learning improve hydrological predictions in the alpine regions?

Yao，Yingying1; Zhao，Yufeng1; Li，Xin2; Feng，Dapeng3; Shen，Chaopeng3; Liu，Chuankun4; Kuang，Xingxing5; Zheng，Chunmiao5,6

2023-10-01

10.1016/j.jhydrol.2023.130038

Journal of Hydrology   Impact Factor & Quartile

0022-1694

1879-2707

The Tibetan Plateau (TP) is an important Asian water tower for livelihood, irrigation, hydropower, and downstream ecosystems. Hydrological predictions in the TP have long been limited by sparse and discontinuous observations. Transfer learning (TL) technology may improve hydrological predictions by pre-training deep learning (DL) models on data-rich areas and then applying them to data-limited areas. However, the extent to which the DL and TL models work in alpine regions and the physical knowledge they provide remain unclear. Models were pretrained using data from 671 catchments across the U.S. and fine-tuned using data from four basins around the TP. Our results show that streamflow data with different temporal resolutions (monthly or daily) have little effect on discharge predictions when using DL. The number of discharge observations needed to enable acceptable performance of the DL models (Nash-Sutcliffe Efficiency coefficient greater than 0.6) depends on the hydrological characteristics of the catchments, in particular, how closely they conform to a general rainfall-runoff system. Climate forcing data determine the performance of streamflow prediction, whereas other attributes (i.e., soil and geology) have less significant impacts on prediction. The effectiveness of the DL and TL models is limited because groundwater contributes significantly to river discharge. This study provides an updated understanding of the application of DL and TL to quantify hydrological changes in the global cryosphere environment.

Deep learning Streamflow prediction Tibetan Plateau Transfer learning

SCI

English

Others

National Natural Science Foundation of China["92047202","41901023","42107096"]

Engineering ; Geology ; Water Resources

Engineering, Civil ; Geosciences, Multidisciplinary ; Water Resources

WOS:001077517400001

ELSEVIER

ENGINEERING

2-s2.0-85170068039

Scopus

1.Institute of Global Environmental Change,Xi'an Jiaotong University,Xi'an,China
2.National Tibetan Plateau Data Center,State Key Laboratory of Tibetan Plateau Earth System Science (LATPES),Institute of Tibetan Plateau Research,Chinese Academy of Sciences,Beijing,China
3.Civil and Environmental Engineering,Pennsylvania State University,University Park,United States
4.Sichuan Academy of Environmental Policy and Planning,Chengdu,China
5.State Environmental Protection Key Laboratory of Integrated Surface Water-Groundwater Pollution Control,School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen,China
6.EIT Institute for Advanced Study,Ningbo,China

Yao，Yingying,Zhao，Yufeng,Li，Xin,et al. Can transfer learning improve hydrological predictions in the alpine regions?[J]. Journal of Hydrology,2023,625.

Yao，Yingying.,Zhao，Yufeng.,Li，Xin.,Feng，Dapeng.,Shen，Chaopeng.,...&Zheng，Chunmiao.(2023).Can transfer learning improve hydrological predictions in the alpine regions?.Journal of Hydrology,625.

Yao，Yingying,et al."Can transfer learning improve hydrological predictions in the alpine regions?".Journal of Hydrology 625(2023).