Exploring the Potential of Long Short-Term Memory Networks for Improving Understanding of Continental- and Regional-Scale Snowpack Dynamics

Yuan Heng Wang, Hoshin V. Gupta, Xubin Zeng, Guo Yue Niu

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

Accurate estimation of the spatio-temporal distribution of snow water equivalent is essential given its global importance for understanding climate dynamics and climate change, and as a source of fresh water. Here, we explore the potential of using the Long Short-Term Memory (LSTM) network for continental and regional scale modeling of daily snow accumulation and melt dynamics at 4-km pixel resolution across the conterminous US (CONUS). To reduce training costs (data are available for ∼0.31 million snowy pixels), we combine spatial sampling with stagewise model development, whereby the network is first pretrained across the entire CONUS and then subjected to regional fine-tuning. Accordingly, model evaluation is focused on out-of-sample predictive performance across space (analogous to the prediction in ungauged basins problem). We find that, given identical inputs (precipitation, temperature, and elevation), a single CONUS-wide LSTM provides significantly better spatio-temporal generalization than a regionally calibrated version of the physical-conceptual temperature-index-based SNOW17 model. Adding more meteorological information (dew point temperature, vapor pressure deficit, longwave radiation, and shortwave radiation) further improves model performance, while rendering redundant the local information provided by elevation. Overall, the LSTM exhibits better transferability than SNOW17 to locations that were not included in the training data set, reinforcing the advantages of structure learning over parameter learning. Our results suggest that an LSTM-based approach could be used to develop continental/global-scale systems for modeling snow dynamics.

Original languageEnglish
Article numbere2021WR031033
JournalWater Resources Research
Volume58
Issue number3
DOIs
StatePublished - Mar 2022
Externally publishedYes

Funding

This work was partially supported by grants NA18OAR4590397 from the National Oceanic and Atmospheric Administration (NOAA) OAR's OWAQ. The second author acknowledges partial support by the Australian Centre of Excellence for Climate System Science (CE110001028). The authors would like to thank the WRR editorial team including Charles Luce (Editor), the Associate Editor, reviewer Thorsten Wagner, and two anonymous reviewers for taking their time to provide constructive comments. Further thanks are due to Sungwook Wi and Tirthankar Roy for providing the SNOW17 code and Patrick Broxton for discussions regarding the data used, and to Andrew Bennett, Luis De La Fuente and Mohammad Reza Ehsani for pre-reviewing the early version of manuscript. This work was partially supported by grants NA18OAR4590397 from the National Oceanic and Atmospheric Administration (NOAA) OAR's OWAQ. The second author acknowledges partial support by the Australian Centre of Excellence for Climate System Science (CE110001028). The authors would like to thank the WRR editorial team including Charles Luce (Editor), the Associate Editor, reviewer Thorsten Wagner, and two anonymous reviewers for taking their time to provide constructive comments. Further thanks are due to Sungwook Wi and Tirthankar Roy for providing the SNOW17 code and Patrick Broxton for discussions regarding the data used, and to Andrew Bennett, Luis De La Fuente and Mohammad Reza Ehsani for pre‐reviewing the early version of manuscript.

FundersFunder number
Australian Centre of Excellence for Climate System ScienceCE110001028
Sungwook Wi and Tirthankar Roy
National Oceanic and Atmospheric Administration

    Keywords

    • LSTMs
    • SNOW17
    • deep learning
    • snow accumulation and melt

    Fingerprint

    Dive into the research topics of 'Exploring the Potential of Long Short-Term Memory Networks for Improving Understanding of Continental- and Regional-Scale Snowpack Dynamics'. Together they form a unique fingerprint.

    Cite this