Extended Range Arctic Sea Ice Forecast with Convolutional Long-Short Term Memory Networks

Abstract

Operational Arctic sea ice forecasts are of crucial importance to science and to society in the Arctic region. Currently, statistical and numerical climate models are widely used to generate the Arctic sea ice forecasts at weather time-scales. Numerical models require near real-time input of relevant environmental conditions consistent with the model equations and they are computationally expensive. In this study, we propose a deep learning approach, namely Convolutional Long Short Term Memory Networks (ConvLSTM), to forecast sea ice in the Barents Sea at weather to sub-seasonal time scales. This is an unsupervised learning approach. It makes use of historical records and it exploits the covariances between different variables, including spatial and temporal relations. With input fields from reanalysis data, we demonstrate that ConvLSTM is able to learn the variability of the Arctic sea ice and can forecast regional sea ice concentration skillfully at weekly to monthly time scales. It preserves the physical consistency between predictors and predictands, and generally outperforms forecasts with climatology, persistence and a statistical model. Based on the known sources of predictability, sensitivity tests with different climate fields as input for learning were performed. The impact of different predictors on the quality of the forecasts are evaluated and we demonstrate that the surface energy budget components have a large impact on the predictability of sea ice at weather time scales. This method is promising to enhance operational Arctic sea ice forecasting in the near future.

Subseasonal Prediction of Regional Antarctic Sea Ice by a Deep Learning Model

“…Given the paucity of observations and challenges in simulating sea ice physics in the Antarctic, is it feasible to pursue an alternative approach by utilizing deep‐learning (DL) methodology for sea ice forecasting at the subseasonal scale? By extracting sea ice spatiotemporal features at multiple scales, DL has an immense potential to capture signals of sea ice predictability and avoid errors caused by incomplete parameterization in the complicated ocean‐atmosphere‐ice system (Andersson et al., 2021; Chi & Kim, 2017; Kim et al., 2020; Liu et al., 2021). In this study, we develop a DL model called sea ice prediction network (SIPNet) to predict subseasonal Antarctic sea ice concentration (SIC) using only SIC as input.…”

Short-term Forecasting of Sea Ice Thickness Based on PredRNN++

“…Therefore, in the face of the advantages and shortcomings of LSTM and CNNs, ConvLSTM was born, which can handle both the information of temporal dimension and spatial information extraction. Some scholars have taken advantage of the ConvLSTM model to achieve weeklyscale forecasts of sea ice concentration in the Arctic Barents Sea domain based on weekly average information of sea ice density [15]. Liu et al achieved a daily forecast of sea ice concentration based on ConvLSTM, and the performance was improved by 13% compared to using CNNs only [16].…”

Seasonal prediction and possible causes of sudden losses of sea-ice in the Weddell Sea in recent years based on potential oceanic and atmospheric factors

“…Machine learning, particularly deep learning, has also been recently used to predict sea-ice variation to tackle non-linear interaction issues (Kim et al, 2020;Liu et al, 2021a). Liu et al (2021b) trained convolutional long short-term memory (ConvLSTM) networks to predict SIC at weather to sub-seasonal scales in the Barents Sea. Whereas the prediction of Antarctic sea-ice has only recently received widespread international attention, it has received relatively little research.…”