Wright, NC; Polashenski, CM (2020). How Machine Learning and High-Resolution Imagery Can Improve Melt Pond Retrieval From MODIS Over Current Spectral Unmixing Techniques. JOURNAL OF GEOPHYSICAL RESEARCH-OCEANS, 125(2), e2019JC015569.

Meltwater that pools on the surface of Arctic sea ice enhances solar absorption and accelerates further ice melt. The impact of melt ponds on energy absorption is controlled primarily through their influence on ice albedo, which is, in turn, governed in large part by the ponds' spatial coverage. This work seeks to observe the spatial coverage of melt ponds across the Arctic basin with sufficient accuracy to investigate pond-albedo feedback and presents an improved technique to achieve this goal. We approach the problem by using the Open Source Sea Ice Processing algorithm to classify surface features in submeter resolution optical satellite imagery over select sites where such imagery is available. These data establish "true" estimates of pond coverage and the ponds' spectral reflectance. This information is then used to inform, improve, and test spectral unmixing and machine learning techniques that seek to determine melt pond coverage from more widely available, but lower resolution, optical satellite imagery (e.g., Moderate Resolution Imaging Spectroradiometer). The new machine learning approach improves accuracy from prior work and can contribute to improved efforts to validate melt pond models or understand trends in pond coverage. Nevertheless, we encounter and carefully document significant challenges to retrieving melt pond fractions from low-resolution optical imagery. These limit accuracy to levels below that necessary for resolving climatologically important trends. We conclude that greatly expanding the collection of highresolution satellite imagery over sea ice is necessary to monitor melt pond coverage with the accuracy needed by the scientific community. Plain Language Summary As temperatures in the Arctic rise during summer months, meltwater pools on the surface of sea ice. These ponds are darker than snow/ice and cause more sunlight to be absorbed. This creates a feedback cycle that accelerates ice melt. A primary factor in this cycle is the percentage of the ice surface that is covered by ponds. It is therefore important to observe the spatial coverage of ponds across the Arctic to better understand their impact sea ice loss. Due to the remoteness of the Arctic Ocean, it is necessary to utilize satellite imagery to investigate the properties of sea ice. In satellite imagery there is a trade-off between resolution and spatial coverage: Images can be either "sharp," seeing many details of the surface but covering a small region, or "blurry" covering a large region but where each pixel contains many ponds. This work seeks to improve techniques (called spectral unmixing) for determining the fraction of each low-resolution pixel that is a pond. We investigate the theoretical limits of spectral unmixing and conclude that it has several limitations that negatively impact its usefulness. Finally, we trial a new machine learning approach to the same problem that shows promising results.