Sentinel-1 C-band synthetic aperture radar (SAR) images can be used to observe the drift of icebergs over the Southern Ocean with around 1–3 d of temporal resolution and 10–40 m of spatial resolution. The Google Earth Engine (GEE) cloud-based platform allows processing of a large quantity of Sentinel-1 images, saving time and computational resources. In this study, we process Sentinel-1 data via GEE to detect and track the drift of iceberg B43 during its lifespan of 3 years (2017–2020) in the Southern Ocean. First, to detect all candidate icebergs in Sentinel-1 images, we employ an object-based image segmentation (simple non-iterative clustering – SNIC) and a traditional backscatter threshold method. Next, we automatically choose and trace the location of the target iceberg by comparing the centroid distance histograms (CDHs) of all detected icebergs in subsequent days with the CDH of the reference target iceberg. Using this approach, we successfully track iceberg B43 from the Amundsen Sea to the Ross Sea and examine its changes in area, speed, and direction. Three periods with sudden losses of area (i.e., split-offs) coincide with periods of low sea ice concentration, warm air temperature, and high waves. This implies that these variables may be related to mechanisms causing the split-off of the iceberg. Since the iceberg is generally surrounded by compacted sea ice, its drift correlates in part with sea ice motion and wind velocity. Given that the bulk of the iceberg is under water (∼30–60 m freeboard and ∼150–400 m thickness), its motion is predominantly driven by the westward-flowing Antarctic Coastal Current, which dominates the circulation of the region. Considering the complexity of modeling icebergs, there is a demand for a large iceberg database to better understand the behavior of icebergs and their interactions with surrounding environments. The semi-automated iceberg tracking based on the storage capacity and computing power of GEE can be used for this purpose.

Forecasting sea ice concentration (SIC) and sea ice velocity (SIV) in the Arctic Ocean is of great significance as the Arctic environment has been changed by the recent warming climate. Given that physical sea ice models require high computational costs with complex parameterization, deep learning techniques can effectively replace the physical model and improve the performance of sea ice prediction. This study proposes a novel multi-task fully conventional network architecture named hierarchical information-sharing U-net (HIS-Unet) to predict daily SIC and SIV. Instead of learning SIC and SIV separately at each branch, we allow the SIC and SIV layers to share their information and assist each other’s prediction through the weighting attention modules (WAMs). Consequently, our HIS-Unet outperforms other statistical approaches, sea ice physical models, and neural networks without such information-sharing units. The improvement of HIS-Unet is more significant to when and where SIC changes seasonally, which implies that the information sharing between SIC and SIV through WAMs helps learn the dynamic changes of SIC and SIV. The weight values of the WAMs imply that SIC information plays a more critical role in SIV prediction, compared to that of SIV information in SIC prediction, and information sharing is more active in marginal ice zones (e.g., East Greenland and Hudson/Baffin Bays) than in the central Arctic.

The power capacity of solar photovoltaics (PVs) in Korea has grown dramatically in recent years, and an accurate estimation of solar resources is crucial for the efficient management of these solar PV systems. Since the number of solar irradiance measurement sites is insufficient for Korea, satellite images can be useful sources for estimating solar irradiance over a wide area of Korea. In this study, an artificial neural network (ANN) model was constructed to calculate hourly global horizontal solar irradiance (GHI) from Korea Communication, Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) images. Solar position variables and five COMS MI channels were used as inputs for the ANN model. The basic ANN model was determined to have a window size of five for the input satellite images and two hidden layers, with 30 nodes on each hidden layer. After these ANN parameters were determined, the temporal and spatial applicability of the ANN model for solar irradiance mapping was validated. The final ANN ensemble model, which calculated the hourly GHI from 10 independent ANN models, exhibited a correlation coefficient (R) of 0.975 and root mean square error (RMSE) of 54.44 W/m² (12.93%), which were better results than for other remote-sensing based works for Korea. Finally, GHI maps for Korea were generated using the final ANN ensemble model. This COMS-based ANN model can contribute to the efficient estimation of solar resources and the improvement of the operational efficiency of solar PV systems for Korea.

Calving is responsible for the retreat, acceleration, and thinning of numerous tidewater glaciers in Greenland. An accurate representation of this process in ice sheet numerical models is critical to better predict the future response of the ice sheet to climate change. While traditional numerical models have been used to simulate ice dynamics and calving under specific parameterized conditions, the computational demand of these models makes it difficult to efficiently fine-tune these parameterizations, adding to the overall uncertainty in future sea level rise. In this study, we adopt three standard graph neural network (GNN) architectures, including graph convolutional network, graph attention network, and equivariant graph convolutional network (EGCN), to develop surrogate models for finite-element simulations from the Ice-sheet and Sea-level System Model. GNNs are particularly well-suited for this problem as they naturally capture the representation of unstructured meshes used by finite-element models. When these GNNs are trained with numerical simulations of Helheim Glacier, Greenland, for different calving stress thresholds, they successfully reproduce the observed evolution of ice velocity, ice thickness, and ice front migration between 2007 and 2020. Moreover, these emulators exhibit uncertainties of less than 10 %–20 % when extrapolating to out-of-sample calving parameterization cases. Among the three GNN architectures, EGCN outperforms the others by preserving the equivariance of graph structures. By leveraging the GPU-based GNN emulators, which are 30–34 times faster than traditional numerical simulations, we determine the temporal variations of the optimal calving threshold that minimizes the misfit between modeled and observed ice fronts. This fine-tuned calving parameterization, enabled by GNN emulators, can enhance the reliability of numerical models in capturing glacier mass loss driven by calving.

NASA’s ICESat-2 has been providing sea ice freeboard measurements across the polar regions since October 2018. In spite of the outstanding spatial resolution and precision of ICESat-2, the spatial sparsity of the data can be a critical issue for sea ice monitoring. This study employs a geostatistical approach (i.e., ordinary kriging) to characterize the spatial autocorrelation of the ICESat-2 freeboard measurements (ATL10) to estimate weekly freeboard variations in 2019 for the entire Ross Sea area, including where ICESat-2 tracks are not directly available. Three variogram models (exponential, Gaussian, and spherical) are compared in this study. According to the cross-validation results, the kriging-estimated freeboards show correlation coefficients of 0.56–0.57, root mean square error (RMSE) of ~0.12 m, and mean absolute error (MAE) of ~0.07 m with the actual ATL10 freeboard measurements. In addition, the estimated errors of the kriging interpolation are low in autumn and high in winter to spring, and low in southern regions and high in northern regions of the Ross Sea. The effective ranges of the variograms are 5–10 km and the results from the three variogram models do not show significant differences with each other. The southwest (SW) sector of the Ross Sea shows low and consistent freeboard over the entire year because of the frequent opening of wide polynya areas generating new ice in this sector. However, the southeast (SE) sector shows large variations in freeboard, which demonstrates the advection of thick multiyear ice from the Amundsen Sea into the Ross Sea. Thus, this kriging-based interpolation of ICESat-2 freeboard can be used in the future to estimate accurate sea ice production over the Ross Sea by incorporating other remote sensing data.

The Ice-sheet and Sea-level System Model (ISSM) provides numerical solutions for ice sheet dynamics using finite element and fine mesh adaption. However, considering ISSM is compatible only with central processing units (CPUs), it has limitations in economizing computational time to explore the linkage between climate forcings and ice dynamics. Although several deep learning emulators using graphic processing units (GPUs) have been proposed to accelerate ice sheet modeling, most of them rely on convolutional neural networks (CNNs) designed for regular grids. Since they are not appropriate for the irregular meshes of ISSM, we use a graph convolutional network (GCN) to replicate the adapted mesh structures of the ISSM. When applied to transient simulations of the Pine Island Glacier (PIG), Antarctica, the GCN successfully reproduces ice thickness and velocity with a correlation coefficient of approximately 0.997, outperforming non-graph models, including fully convolutional network (FCN) and multi-layer perceptron (MLP). Compared to the fixed-resolution approach of the FCN, the flexible-resolution structure of the GCN accurately captures detailed ice dynamics in fast-ice regions. By leveraging 60–100 times faster computational time of the GPU-based GCN emulator, we efficiently examine the impacts of basal melting rates on the ice sheet dynamics in the PIG.