Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting

TL;DR

This paper develops a U-Net based deep learning model for short-term daily sea ice forecasting, demonstrating its effectiveness and generalization across multiple Arctic regions to support safer marine operations amid climate change.

Contribution

It introduces a practical, real-time capable deep learning approach for operational sea ice prediction, addressing the gap in daily forecasting and regional generalization.

Findings

U-Net outperforms simple baselines in sea ice prediction

Using additional weather data improves forecast accuracy

Model generalizes well across multiple Arctic regions

Abstract

Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe. While ocean-ice numerical models are highly computationally intensive, relatively lightweight ML-based methods may be more efficient in this task. Many works have exploited different deep learning models alongside classical approaches for predicting sea ice concentration in the Arctic. However, only a few focus on daily operational forecasts and consider the real-time availability of data they need for operation. In this work, we aim to close this gap and investigate the performance of the U-Net model trained in two regimes for predicting sea ice for up to the next 10 days. We show that this deep learning model can outperform simple baselines by a significant margin and improve its quality by using additional weather data and training on multiple regions, ensuring its generalization abilities. As a practical outcome, we build a fast and flexible tool that produces operational sea ice forecasts in the Barents Sea, the Labrador Sea, and the Laptev Sea regions.