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.

@en

Few studies have assessed a comprehensive understanding of how the seasonal and interannual variability and trends of the surface mass balance (SMB), including the influence of atmospheric river (ARs), are governed by the climate on the South Shetland Islands (SSI) glaciers located in the northerly Antarctic Peninsula (AP). To address this gap, we comprehensively analyzed the correlations and regressions between seasonal and annual SMB with regional to global climate indices and a state-of-the-art AR tracking database from 1980 to 2019. The daily and monthly SMB was obtained from two physical glaciological models, which was verified against 19 years of annual and seasonal glacier-wide SMB observations available in three glaciers (Johnsons, Hurd, and Bellingshausen), showing a good ability to capture interannual and seasonal variability. Results indicate a low dependence of the SMB on main atmospheric modes of variability (e.g., El Niño-Southern Oscillation and the Southern Annular Mode), and a moderate dependence on regional climate indices based on atmospheric pressure anomalies and sea surface temperature anomalies over the Drake Passage. Furthermore, our findings reveal that ARs have different effects on the SMB depending on the season. For example, winter ARs tend to boost accumulation due to increased snowfall, while summer ARs tend to intensify surface melting due to increased sensible heat flux. Our study highlights the Drake Passage as a key region that has the potential to influence the interannual and seasonal variability of the SMB and other climate variables, such as air temperature and snowfall over the SSI. We suggest that future work should consider this region to better understand the past, present and future climate changes on the SSI and surrounding areas.

@en

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.

@en

Geoscientific models are facing increasing challenges to exploit growing datasets coming from remote sensing. Universal differential equations (UDEs), aided by differentiable programming, provide a new scientific modelling paradigm enabling both complex functional inversions to potentially discover new physical laws and data assimilation from heterogeneous and sparse observations. We demonstrate an application of UDEs as a proof of concept to learn the creep component of ice flow, i.e. a nonlinear diffusivity differential equation, of a glacier evolution model. By combining a mechanistic model based on a two-dimensional shallow-ice approximation partial differential equation with an embedded neural network, i.e. a UDE, we can learn parts of an equation as nonlinear functions that then can be translated into mathematical expressions. We implemented this modelling framework as ODINN.jl, a package in the Julia programming language, providing high performance, source-to-source automatic differentiation (AD) and seamless integration with tools and global datasets from the Open Global Glacier Model in Python. We demonstrate this concept for 17 different glaciers around the world, for which we successfully recover a prescribed artificial law describing ice creep variability by solving ∼ 500 000 ordinary differential equations in parallel. Furthermore, we investigate which are the best tools in the scientific machine learning ecosystem in Julia to differentiate and optimize large nonlinear diffusivity UDEs. This study represents a proof of concept for a new modelling framework aiming at discovering empirical laws for large-scale glacier processes, such as the variability in ice creep and basal sliding for ice flow, and new hybrid surface mass balance models.@en