AUTHOR=Yang Kehan , John Aji , Shean David , Lundquist Jessica D. , Sun Ziheng , Yao Fangfang , Todoran Stefan , Cristea Nicoleta 

TITLE=High-resolution mapping of snow cover in montane meadows and forests using Planet imagery and machine learning

JOURNAL=Frontiers in Water

VOLUME=Volume 5 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/water/articles/10.3389/frwa.2023.1128758

DOI=10.3389/frwa.2023.1128758

ISSN=2624-9375

ABSTRACT=Mountain snowpack provides critical water resources in forest and meadow ecosystems that are experiencing rapid change due to global warming. Understanding the heterogeneity of time-varying mountain snowpack requires high spatiotemporal resolution snow cover data. Yet, most existing snow cover datasets have spatial resolution that is too coarse to map snow cover in small meadows and forest gaps or temporal resolution that is too coarse to capture rapid changes in snow-covered area (SCA). To advance our observation skills of snow cover in montane meadows and forests, we developed a machine learning model to produce near-daily SCA maps at 3-m resolution from PlanetScope imagery. The results show that the model achieves a median F1 score of 0.75 for 103 cloud-free images across four different sites in the Western United States and Switzerland. The model has a higher accuracy (F1 score = 0.82) when forest areas are excluded during evaluation. Larger meadows with simple geometry had higher SCA accuracy than smaller or more complex meadows. The median F1 score was 0.83 for 7741 meadows at the two study sites in Sierra Nevada, California. While mapping SCA in regions close to or under forest canopy is still challenging, the model is capable of accurately mapping SCA for relatively large forest gaps (i.e., 15 m < DCE < 27 m) and areas very close (> 10 m) to forest edges, improving our SCA mapping ability in forested areas. Our approach can be used to map SCA from other remote sensing datasets, including other high spatial resolution optical satellites, which will benefit ecohydrological studies in a world expecting significant changes in snow.