Because Antarctic surface melt is mostly driven by local processes, its simulation necessitates high-resolution regional climate models (RCMs). However, the current horizontal resolution of RCMs (≈25–30 km) is inadequate for capturing small-scale melt processes. To address this limitation, we present SUPREME (SUPer-REsolution-based Melt Estimation over Antarctica), a deep learning method to downscale surface melt to 5.5 km resolution using a physically-informed super-resolution model. The physical information integrated into the model originates from observations tied to surface melt, specifically remote sensing-derived albedo and elevation. These remote sensing data, in addition to a Regional Atmospheric Climate Model (RACMO) run at 27 km resolution, account for the diverse drivers of surface melt across Antarctica, facilitating effective generalization beyond the training region of the Antarctic Peninsula. A comparison of SUPREME with a dynamically downscaled RACMO run at 5.5 km over the Antarctic Peninsula shows high accuracy, with average yearly RMSE and bias of 5.5 mm w.e. yr⁻¹ and 4.5 mm w.e. yr⁻¹, respectively. Validation at five automatic weather stations reveals SUPREME's marked improvement with substantially lower average RMSE (81 mm w.e.) compared to RACMO 27 km (129 mm w.e.). Beyond the training region, SUPREME aligns more closely with remote sensing products associated with surface melt than super-resolution models lacking physical constraints. While further validation of SUPREME is needed, our study highlights the potential of super-resolution techniques with physical constraints for high-resolution surface melt monitoring in Antarctica, providing insights into the impacts of localized melting on processes affecting ice shelf integrity such as hydrofracturing.

While the influence of surface melt on Antarctic ice shelf stability can be large, the duration and affected area of melt events are often small. Therefore, melt events are difficult to capture with remote sensing, as satellite sensors always face the trade-off between spatial and temporal resolution. To overcome this limitation, we developed UMelt: a surface melt record for all Antarctic ice shelves with a high spatial (500 m) and high temporal (12 h) resolution for the period 2016–2021. Our approach is based on a deep learning model, specifically a U-Net, which was developed in Google Earth Engine. The U-Net combines microwave remote sensing observations from three sources: Sentinel-1, Special Sensor Microwave Imager/Sounder (SSMIS), and Advanced Scatterometer (ASCAT). The U-Net was trained on the Shackleton Ice Shelf for melt seasons 2017–2021, using the fine-scale melt patterns of Sentinel-1 as reference data and SSMIS, ASCAT, a digital elevation model, and multi-year Sentinel-1 melt fraction as predictors. The trained U-Net performed well on the Shackelton Ice Shelf for test melt season 2016–2017 (accuracy: 91.3%; F1-score: 86.9%), and the Larsen C Ice Shelf, which was not considered during training (accuracy: 91.0%; F1-score: 89.3%). Using the trained U-Net model, we have successfully developed the UMelt record. UMelt allows Antarctic-wide surface melt to be detected at a small scale while preserving a high temporal resolution, which could lead to new insights into the response of ice shelves to a changing atmospheric forcing.

Antarctic blue ice areas are exposed due to erosion and sublimation of snow. At the same time, surface melt can form surface types that are spectrally similar to blue ice, especially at low elevations. These are termed melt-induced blue ice areas. Both types of blue ice are sensitive indicators of climate change. Satellite remote sensing is a powerful technique to retrieve the spatial extent of blue ice areas and their variation in time. Yet, existing satellite-derived blue ice area products are either mono-temporal for the entire Antarctic ice sheet, or multi-temporal for a limited area. Here, we present FABIAN, a product of blue ice fraction over Antarctica, derived from the moderate resolution imaging spectroradiometer (MODIS) archive covering the period 2000–2021. A spectral mixture analysis (SMA) in Google Earth Engine, based on a careful selection of endmember spectra, accurately reconstructs the reflectance observed by MODIS in blue ice areas. Based on a validation with contemporaneous Sentinel-2 images, FABIAN has a root mean square error in blue ice fraction of approximately 10% ∼ 20% in wind-induced blue ice areas, and 20% ∼ 30% in melt-induced blue ice areas across six selected test sites in the coastal East Antarctic ice sheet. FABIAN is challenged in regions with shallow melt streams and lakes, since their spectral profiles are similar to those from blue ice areas in MODIS bands. For further analyses and applications, FABIAN holds the potential for (1) deriving annual blue ice area maps, (2) distinguishing between wind-and melt-induced blue ice types, (3) evaluating and correcting (regional) climate models, and (4) analyzing temporal variations in blue ice abundance and exposure.

Surface melt is an important driver of ice shelf disintegration and its consequent mass loss over the Antarctic Ice Sheet. Monitoring surface melt using satellite remote sensing can enhance our understanding of ice shelf stability. However, the sensors do not measure the actual physical process of surface melt, but rather observe the presence of liquid water. Moreover, the sensor observations are influenced by the sensor characteristics and surface properties. Therefore, large inconsistencies can exist in the derived melt estimates from different sensors. In this study, we apply state-of-the-art melt detection algorithms to four frequently used remote sensing sensors, i.e., two active microwave sensors, which are Advanced Scatterometer (ASCAT) and Sentinel-1, a passive microwave sensor, i.e., Special Sensor Microwave Imager/Sounder (SSMIS), and an optical sensor, i.e., Moderate Resolution Imaging Spectroradiometer (MODIS). We intercompare the melt detection results over the entire Antarctic Ice Sheet and four selected study regions for the melt seasons 2015-2020. Our results show large spatiotemporal differences in detected melt between the sensors, with particular disagreement in blue ice areas, in aquifer regions, and during wintertime surface melt. We discuss that discrepancies between sensors are mainly due to cloud obstruction and polar darkness, frequency-dependent penetration of satellite signals, temporal resolution, and spatial resolution, as well as the applied melt detection methods. Nevertheless, we argue that different sensors can complement each other, enabling improved detection of surface melt over the Antarctic Ice Sheet.

Accurately estimating the surface melt volume of the Antarctic Ice Sheet is challenging and has hitherto relied on climate modeling or observations from satellite remote sensing. Each of these methods has its limitations, especially in regions with high surface melt. This study aims to demonstrate the potential of improving surface melt simulations with a regional climate model by deploying a deep learning model. A deep-learning-based framework has been developed to correct surface melt from the regional atmospheric climate model version 2.3p2 (RACMO2), using meteorological observations from automatic weather stations (AWSs) and surface albedo from satellite imagery. The framework includes three steps: (1) training a deep multilayer perceptron (MLP) model using AWS observations, (2) correcting Moderate Resolution Imaging Spectroradiometer (MODIS) albedo observations, and (3) using these two to correct the RACMO2 surface melt simulations. Using observations from three AWSs at the Larsen B and C ice shelves, Antarctica, cross-validation shows a high accuracy (root-mean-square error of 0.95ĝ€¯mmĝ€¯w.e.ĝ€¯d-1, mean absolute error of 0.42ĝ€¯mmĝ€¯w.e.ĝ€¯d-1, and a coefficient of determination of 0.95). Moreover, the deep MLP model outperforms conventional machine learning models and a shallow MLP model. When applying the trained deep MLP model over the entire Larsen Ice Shelf, the resulting corrected RACMO2 surface melt shows a better correlation with the AWS observations for two out of three AWSs. However, for one location (AWS 18), the deep MLP model does not show improved agreement with AWS observations; this is likely because surface melt is largely driven by factors (e.g., air temperature, topography, katabatic wind) other than albedo within the corresponding coarse-resolution model pixels. Our study demonstrates the opportunity to improve surface melt simulations using deep learning combined with satellite albedo observations. However, more work is required to refine the method, especially for complicated and heterogeneous terrains.