22 Jun 2022
22 Jun 2022
Status: this preprint is open for discussion.

Estimating spatiotemporally continuous snow water equivalent from intermittent satellite track observations using machine learning methods

Xiaoyu Ma1, Dongyue Li1,2, Yiwen Fang2, Steven A. Margulis2, and Dennis P. Lettenmaier1,2 Xiaoyu Ma et al.
  • 1Department of Geography, University of California, Los Angeles, 90095, United States
  • 2Department of Civil & Environmental Engineering, University of California, Los Angeles, 90095, United States

Abstract. Accurate remote sensing-based snow water equivalent (SWE) estimates have been elusive, particularly in mountain areas, however, there now appears to be some potential for direct satellite-based SWE observations along ground tracks that only cover a portion of a spatial domain (e.g., watershed). Fortunately, spatiotemporally continuous meteorological and surface variables could be leveraged to infer SWE in the gaps between satellite ground tracks. Here, we evaluate statistical and machine learning (ML) approaches to perform a track-to-area (TTA) transformation of synthetic SWE observations in California’s Upper Tuolumne River Watershed. We construct relationships between multiple meteorological and surface variables and synthetic SWE observations along observation tracks, and we then extend this relationship to unobserved areas between ground tracks to estimate SWE over the entire watershed. Domain-wide April 1st SWE inferred using two satellite tracks (~4.5 % basin coverage) resulted in percent error of basin-averaged SWE of 24.5 %, 4.5 %, and 6.3 % in an extreme dry year (WY2015), a normal year (WY2008) and an extraordinarily wet year (WY2017), respectively. Assuming a 10-day overpass interval, percent errors in basin-averaged SWE in both snow accumulation and snowmelt seasons were mostly less than 10 %. We employ feature sensitivity analysis to overcome the black-box nature of ML methods and increase the explainability of the ML results. Our feature sensitivity analysis shows that precipitation is the dominant variable controlling the TTA SWE estimation, followed by net longwave radiation. We find a modest increase in SWE estimation accuracy when more than two ground tracks are leveraged. Accuracy of Apr 1st SWE estimation is only modestly improved for track repeats more often than about 15 days.

Xiaoyu Ma et al.

Status: open (until 17 Aug 2022)

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

Xiaoyu Ma et al.


Total article views: 191 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
137 47 7 191 15 2 4
  • HTML: 137
  • PDF: 47
  • XML: 7
  • Total: 191
  • Supplement: 15
  • BibTeX: 2
  • EndNote: 4
Views and downloads (calculated since 22 Jun 2022)
Cumulative views and downloads (calculated since 22 Jun 2022)

Viewed (geographical distribution)

Total article views: 100 (including HTML, PDF, and XML) Thereof 100 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 02 Jul 2022
Short summary
We explore satellite retrievals of snow water equivalent (SWE) along hypothetical ground tracks that would allow estimation of SWE over an entire watershed. Retrieval of SWE from satellites has proved elusive, but there are now technological options that do so along essentially one-dimensional tracks. We use machine learning algorithms as the basis for a track to area (TTA) transformation and show that at least one is robust enough to estimate domain-wide SWE with high accuracy.