Preprints
https://doi.org/10.5194/essd-2021-344
https://doi.org/10.5194/essd-2021-344

  08 Nov 2021

08 Nov 2021

Review status: this preprint is currently under review for the journal ESSD.

Reconstruction of daily gridded snow water equivalent product for the Pan-Arctic region based on a ridge regression machine learning approach

Donghang Shao1,2, Hongyi Li1,2, Jian Wang1,2, Xiaohua Hao1,2, Tao Che1,2, and Wenzheng Ji1,2 Donghang Shao et al.
  • 1Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, 730000, China
  • 2Heihe Remote Sensing Experimental Research Station, Key Laboratory of Remote Sensing of Gansu Province, Chinese Academy of Sciences, Lanzhou, 730000, China

Abstract. Snow water equivalent is an important parameter of the surface hydrological and climate systems, and it has a profound impact on Arctic amplification and climate change. However, there are great differences among existing snow water equivalent products. In the Pan-Arctic region, the existing snow water equivalent products are limited time span and limited spatial coverage, and the spatial resolution is coarse, which greatly limits the application of snow water equivalent data in cryosphere change and climate change studies. In this study, utilizing the ridge regression model (RRM) of a machine learning algorithm, we integrated various existing snow water equivalent (SWE) products to generate a spatiotemporally seamless and high-precision RRM SWE product. The results show that it is feasible to utilize a ridge regression model based on a machine learning algorithm to prepare snow water equivalent products on a global scale. We evaluated the accuracy of the RRM SWE product using Global Historical Climatology Network (GHCN) data and Russian snow survey data. The MAE, RMSE, R, and R2; between the RRM SWE products and observed snow water equivalents are 0.24, 30.29 mm, 0.87, and 0.76, respectively. The accuracy of the RRM SWE dataset is improved by 24 %, 25 %, 32 %, 7 %, and 10 % compared with the original AMSR-E/AMSR2 snow water equivalent dataset, ERA-Interim SWE dataset, Global Land Data Assimilation System (GLDAS) SWE dataset, GlobSnow SWE dataset, and ERA5-land SWE dataset, respectively, and it has a higher spatial resolution. The RRM SWE product production method does not rely too much on an independent snow water equivalent product, it makes full use of the advantages of each snow water equivalent dataset, and it considers the altitude factor. The average MAE of RRM SWE product at different altitude intervals is 0.24 and the average RMSE is 23.55 mm, this method has good stability, it is extremely suitable for the production of snow datasets with large spatial scales, and it can be easily extended to the preparation of other snow datasets. The RRM SWE product is expected to provide more accurate snow water equivalent data for the hydrological model and climate model and provide data support for cryosphere change and climate change studies. The RRM SWE product is available from the ‘A Big Earth Data Platform for Three Poles’ (http://dx.doi.org/10.11888/Snow.tpdc.271556) (Li et al., 2021).

Donghang Shao et al.

Status: open (until 03 Jan 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Donghang Shao et al.

Data sets

Arctic Snow Water Equivalent Grid Dataset (1979-2019) Hongyi Li, Donghang Shao, Haojie Li, Weiguo Wang, Yuan Ma, Huajin Lei http://dx.doi.org/10.11888/Snow.tpdc.271556

Donghang Shao et al.

Viewed

Total article views: 303 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
240 55 8 303 6 6
  • HTML: 240
  • PDF: 55
  • XML: 8
  • Total: 303
  • BibTeX: 6
  • EndNote: 6
Views and downloads (calculated since 08 Nov 2021)
Cumulative views and downloads (calculated since 08 Nov 2021)

Viewed (geographical distribution)

Total article views: 290 (including HTML, PDF, and XML) Thereof 290 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 04 Dec 2021
Download
Short summary
The temporal series and spatial distribution discontinuity of the existing snow water equivalent (SWE) products in the Pan-Arctic region severely restricts the use of SWE data in cryosphere change and climate change studies. Using a ridge regression machine learning algorithm, this study developed a set of spatiotemporally seamless and high-precision SWE products. This product could contribute to the study of cryosphere change and climate change at large spatial scales.