Search

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 0.95 mm w.e. d−1, mean absolute error of 0.42 mm w.e. 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.

Clouds exert a pivotal control on the mass balance of the Greenland and Antarctic Ice Sheet and therefore their contribution to global sea level. Clouds transport moisture onto the marginal ice sheet, where steep topographic gradients force the air to rise and cool, inducing strong orographic precipitation and leaving the interior ice sheet dry (polar desert). Clouds further regulate the radiation balance at the surface and, consequently, surface melt. Depending on their frequency, phase, and structure, clouds not only mute incoming solar radiation but also enhance longwave radiation at the surface. With the advent of novel observations from space (CloudSat-CALIPSO) and in the field, we now have tools to start evaluating the representation of clouds, precipitation, and ice sheet surface radiation in climate models. Here we evaluate the Community Earth System Model version 1 (CESM1(CAM5)) to represent (1) precipitation frequency and phase, using a CALIPSO cloud simulator; (2) cloud radiative effect comparing to a CloudSat-CALIPSO based product; and (3) snowfall amounts and surface mass balance, comparing to CloudSat, in-situ observations, and regional climate model results. After discussing outstanding cloud biases in CESM1(CAM5), we present our efforts to reduce these in the recently released version 2 (CESM2). We show that clouds are considerably better represented in CESM2, leading to improvements in surface radiation, melt, and surface mass balance, although biases in precipitation phase persist. Our work demonstrates the need for high-quality, long-term observations of clouds and their effect on the ice sheet surface to enable continued climate model improvement.