Search for: All records

Abstract Airborne radar sensors capture the profile of snow layers present on top of an ice sheet. Accurate tracking of these layers is essential to calculate their thicknesses, which are required to investigate the contribution of polar ice cap melt to sea-level rise. However, automatically processing the radar echograms to detect the underlying snow layers is a challenging problem. In our work, we develop wavelet-based multi-scale deep learning architectures for these radar echograms to improve snow layer detection. These architectures estimate the layer depths with a mean absolute error of 3.31 pixels and 94.3% average precision, achieving higher generalizability as compared to state-of-the-art snow layer detection networks. These depth estimates also agree well with physically drilled stake measurements. Such robust architectures can be used on echograms from future missions to efficiently trace snow layers, estimate their individual thicknesses, and thus support sea-level rise projection models. 

Abstract. During the concluding phase of the NASA OperationIceBridge (OIB), we successfully completed two airborne measurementcampaigns (in 2018 and 2021, respectively) using a compact S and C band radarinstalled on a Single Otter aircraft and collected data over Alaskanmountains, ice fields, and glaciers. This paper reports seasonal snow depthsderived from radar data. We found large variations in seasonalradar-inferred depths with multi-modal distributions assuming a constantrelative permittivity for snow equal to 1.89. About 34 % of the snowdepths observed in 2018 were between 3.2 and 4.2 m, and close to 30 % of thesnow depths observed in 2021 were between 2.5 and 3.5 m. We observed snowstrata in ice facies, combined percolation and wet-snow facies, and dry-snow facies fromradar data and identified the transition areas from wet-snow facies to icefacies for multiple glaciers based on the snow strata and radarbackscattering characteristics. Our analysis focuses on the measured strataof multiple years at the caldera of Mount Wrangell (K'elt'aeni) to estimate the localsnow accumulation rate. We developed a method for using our radar readingsof multi-year strata to constrain the uncertain parameters of interpretationmodels with the assumption that most of the snow layers detected by theradar at the caldera are annual accumulation layers. At a 2004 ice core and2005 temperature sensor tower site, the locally estimated average snowaccumulation rate is ∼2.89 m w.e. a−1 between the years2003 and 2021. Our estimate of the snow accumulation rate between 2005 and2006 is 2.82 m w.e. a−1, which matches closely to the 2.75 m w.e. a−1 inferred from independent ground-truth measurements made the sameyear. The snow accumulation rate between the years 2003 and 2021 also showeda linear increasing trend of 0.011 m w.e. a−2. This trend iscorroborated by comparisons with the surface mass balance (SMB) derived forthe same period from the regional atmospheric climate model MAR (ModèleAtmosphérique Régional). According to MAR data, which show anincrease of 0.86 ∘C in this area for the period of 2003–2021, thelinear upward trend is associated with the increase in snowfall and rainfallevents, which may be attributed to elevated global temperatures. Thefindings of this study confirmed the viability of our methodology, as wellas its underlying assumptions and interpretation models. 

Climate change is extensively affecting ice sheets resulting in accelerating mass loss in recent decades. Assessment of this reduction and its causes is required to project future ice mass loss. Annual snow accumulation is an important component of the surface mass balance of ice sheets. While in situ snow accumulation measurements are temporally and spatially limited due to their high cost, airborne radar sounders can achieve ice sheet wide coverage by capturing and tracking annual snow layers in the radar images or echograms. In this paper, we use deep learning to uniquely identify the position of each annual snow layer in the Snow Radar echograms taken across different regions over the Greenland ice sheet. We train with more than 15,000 images generated from radar echograms and estimate the thickness of each snow layer within a mean absolute error of 0.54 to 7.28 pixels, depending on dataset. A highly precise snow layer thickness can help improve weather models and, thus, support glaciological studies. Such a well-trained deep learning model can be used with ever-growing datasets to aid in the accurate assessment of snow accumulation on the dynamically changing ice sheets. 

Abstract In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.