An official website of the United States government
Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.
more »
« less
Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation
Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN models still need to undergo scrutiny as higher metrics performance not always translate to adequate outputs. Sea ice type classes are imbalanced, requiring special treatment during training. We evaluate how three different loss functions, some developed for imbalanced class problems, affect the performance of CNN models trained to predict the dominant ice type in Sentinel-1 images. Despite the fact that Dice and Focal loss produce higher metrics, results from cross-entropy seem generally more physically consistent.
more »
« less
- Award ID(s):
- 2026962
- PAR ID:
- 10471120
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium
- ISBN:
- 979-8-3503-2010-7
- Page Range / eLocation ID:
- 145 to 148
- Format(s):
- Medium: X
- Location:
- Pasadena, CA, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract. Arctic sea ice experiences a dramatic annual cycle, and seasonal ice loss and growth can be characterized by various metrics: melt onset, breakup, opening, freeze onset, freeze-up, and closing. By evaluating a range of seasonal sea ice metrics, CMIP6 sea ice simulations can be evaluated in more detail than by using traditional metrics alone, such as sea ice area. We show that models capture the observed asymmetry in seasonal sea ice transitions, with spring ice loss taking about 1–2 months longer than fall ice growth. The largest impacts of internal variability are seen in the inflow regions for melt and freeze onset dates, but all metrics show pan-Arctic model spreads exceeding the internal variability range, indicating the contribution of model differences. Through climate model evaluation in the context of both observations and internal variability, we show that biases in seasonal transition dates can compensate for other unrealistic aspects of simulated sea ice. In some models, this leads to September sea ice areas in agreement with observations for the wrong reasons.more » « less
-
Abstract The predictability of sea ice during extreme sea ice loss events on subseasonal (daily to weekly) time scales is explored in dynamical forecast models. These extreme sea ice loss events (defined as the 5th percentile of the 5-day change in sea ice extent) exhibit substantial regional and seasonal variability; in the central Arctic Ocean basin, most subseasonal rapid ice loss occurs in the summer, but in the marginal seas rapid sea ice loss occurs year-round. Dynamical forecast models are largely able to capture the seasonality of these extreme sea ice loss events. In most regions in the summertime, sea ice forecast skill is lower on extreme sea ice loss days than on nonextreme days, despite evidence that links these extreme events to large-scale atmospheric patterns; in the wintertime, the difference between extreme and nonextreme days is less pronounced. In a damped anomaly forecast benchmark estimate, the forecast error remains high following extreme sea ice loss events and does not return to typical error levels for many weeks; this signal is less robust in the dynamical forecast models but still present. Overall, these results suggest that sea ice forecast skill is generally lower during and after extreme sea ice loss events and also that, while dynamical forecast models are capable of simulating extreme sea ice loss events with similar characteristics to what we observe, forecast skill from dynamical models is limited by biases in mean state and variability and errors in the initialization. Significance Statement We studied weather model forecasts of changes in Arctic sea ice extent on day-to-day time scales in different regions and seasons. We were especially interested in extreme sea ice loss days, or days in which sea ice melts very quickly or is reduced due to diverging forces such as winds, ocean currents, and waves. We find that forecast models generally capture the observed timing of extreme sea ice loss days. We also find that forecasts of sea ice extent are worse on extreme sea ice loss days compared to typical days, and that forecast errors remain elevated following extreme sea ice loss events.more » « less
-
The rapid loss of Arctic sea ice is a striking consequence of anthropogenic global warming. Its remote impacts on mid‐latitude weather and climate have attracted scientific and media attention. In this study, we use a hybrid (dynamical plus machine‐learning) atmospheric model—Google's NeuralGCM—to investigate the mid‐latitude atmospheric circulation responses to Arctic sea‐ice loss for the first time. We conduct experiments in which NeuralGCM is forced with pre‐industrial and future sea‐ice concentrations following the protocol of the Polar Amplification Model Intercomparisom Project. To assess the performance of NeuralGCM, we compare the results with those simulated by two physics‐based climate models. NeuralGCM produces a comparable response of near‐surface warming to sea‐ice loss and the subsequent weakened zonal wind in mid‐latitudes. However, there is a substantial discrepancy between the two models' stratospheric responses, where different temperature responses in these models are associated with different zonal wind and geopotential height responses. Further investigation of North Atlantic blocking shows that NeuralGCM produces stronger, more frequent, and more realistic blocking events. Our results demonstrate the capability of NeuralGCM in simulating the tropospheric responses to Arctic sea‐ice loss, but improvements may be needed for the stratospheric representation.more » « less
-
Sea ice plays a critical role in the global climate system and maritime operations, making timely and accurate classification essential. However, traditional manual methods are time-consuming, costly, and have inherent biases. Automating sea-ice type classification addresses these challenges by enabling faster, more consistent, and scalable analysis. While both traditional and deep-learning approaches have been explored, deep-learning models offer a promising direction for improving efficiency and consistency in sea-ice classification. However, the absence of a standardized benchmark and comparative study prevents a clear consensus on the best-performing models. To bridge this gap, we introduce IceBench, a comprehensive benchmarking framework for sea-ice type classification. Our key contributions are three-fold: First, we establish the IceBench benchmarking framework, which leverages the existing AI4Arctic Sea Ice Challenge Dataset as a standardized dataset, incorporates a comprehensive set of evaluation metrics, and includes representative models from the entire spectrum of sea-ice type-classification methods categorized in two distinct groups, namely pixel-based classification methods and patch-based classification methods. IceBench is open-source and allows for convenient integration and evaluation of other sea-ice type-classification methods, hence facilitating comparative evaluation of new methods and improving reproducibility in the field. Second, we conduct an in-depth comparative study on representative models to assess their strengths and limitations, providing insights for both practitioners and researchers. Third, we leverage IceBench for systematic experiments addressing key research questions on model transferability across seasons (time) and locations (space), data downsampling, and preprocessing strategies. By identifying the best-performing models under different conditions, IceBench serves as a valuable reference for future research and a robust benchmarking framework for the field.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IGARSS52108.2023.10282060
