Terrain-Based Shadow Correction Method for Assessing Supraglacial Features on the Greenland Ice Sheet

Abstract

The presence of shadows in remotely sensed images can reduce the accuracy of land surface classifications. Commonly used methods for removing shadows often use multi-spectral image analysis techniques that perform poorly for dark objects, complex geometric models, or shaded relief methods that do not account for shadows cast on adjacent terrain. Here we present a new method of removing topographic shadows using readily available GIS software. The method corrects for cast shadows, reduces the amount of over-correction, and can be performed on imagery of any spectral resolution. We demonstrate this method using imagery collected with an uncrewed aerial vehicle (UAV) over a supraglacial stream catchment in southwest Greenland. The structure-from-motion digital elevation model showed highly variable topography resulting in substantial shadowing and variable reflectance values for similar surface types. The distribution of bare ice, sediment, and water within the catchment was determined using a supervised classification scheme applied to the corrected and original UAV images. The correction resulted in an insignificant change in overall classification accuracy, however, visual inspection showed that the corrected classification more closely followed the expected distribution of classes indicating that shadow correction can aid in identification of glaciological features hidden within shadowed regions. Shadow correction also caused a substantial decrease in the areal coverage of dark sediment. Sediment cover was highly dependent on the degree of shadow correction (k coefficient), yet, for a correction coefficient optimized to maximize shadow brightness without over-exposing illuminated surfaces, terrain correction resulted in a 49% decrease in the area covered by sediment and a 29% increase in the area covered by water. Shadow correction therefore reduces the overestimation of the dark surface coverage due to shadowing and is a useful tool for investigating supraglacial processes and land cover change over a wide variety of complex terrain.

Time‐lapse photogrammetry reveals hydrological controls of fine‐scale High‐Arctic glacier surface roughness evolution

“…Such depths accord with those of small cryoconite holes and supraglacial rills observed elsewhere in Svalbard (e.g., Rippin et al, 2015; Telling et al, 2012). Because brightness was not normalized across the orthomosaic time‐series, nor corrected for local shadowing (e.g., Leidman et al, 2021), a more robust image calibration (e.g., Ryan et al, 2017a, 2017b; Tedstone et al, 2020) approach would be required to strengthen these tentative spatio‐temporal albedo and roughness associations.…”

Intra-seasonal variability in supraglacial stream sediment on the Greenland Ice Sheet

“…Twentyfive training polygons were used for each of the three classes of each image totaling 600 polygons averaging 1.0 m 2 in area each. This is the same method for classifying sediment areas as published by Leidman et al (2021a) and, since each classification was made using training polygons from the same image, this method effectively accounts for variable solar illumination of the different mosaic images. The location of each classified pixel was then analyzed to determine whether it was found within or outside of the manually digitized stream extent.…”

“…Supraglacial stream drainage networks form in the ablation zone of glaciers around the world (Holmes, 1955;Ferguson, 1973;Marston, 1983;Smith et al, 2015;Watson et al, 2016;Kingslake et al, 2017;Ryan et al, 2018;Lu et al, 2020). These supraglacial stream networks form a series of supraglacial lakes, meandering rivers, and floodplains (flat, sediment-covered regions along the stream banks that are often diurnally inundated with meltwater) as meltwater flows toward moulins (Rennermalm et al, 2013a;Karlstrom et al, 2013;Chu, 2014;Leidman et al, 2021a).…”

“…Sediment is transported onto the surface of the Greenland Ice Sheet by windborne transport from local proglacial moraines and valleys (Bøggild et al, 2010;Nelson et al, 2014;Humbert et al, 2020) as well as, but to a lesser extent, accumulation of fine dust particles from long-range sources such as Asia (Bory et al, 2002;Bory et al, 2003), surface melting of ice containing outcroppings of Pleistocene era long-range dust (Bøggild et al, 2010;Cooper et al, 2018), landslides (Svennevig, 2019), and thrust faulting (Moore et al, 2010). Once on the Ice Sheet, sediment stays distributed on the surface, melts into cryoconite holes, or washes into supraglacial streams (Leidman et al, 2021a).…”

“…The highly turbulent flow characteristics of supraglacial streams (Gleason et al, 2016) would also facilitate a more efficient transfer of energy to the ice for melting. The fact that supraglacial streams display extensive incision compared to the background ablation rates (Ferguson, 1973;Karlstrom et al, 2013;Leidman et al, 2021a) also points to an efficient transfer of energy to the bed. While this incision can lead to shadowing of the stream channel (Leidman et al, 2021b), this effect is only significant in areas of high relief (such as near immediately upstream of moulins).…”