Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery

TL;DR

This paper introduces a novel data-driven method for short-term sea ice forecasting in the Arctic, combining radar imagery, weather data, and uncertainty quantification to improve reliability and safety in maritime operations.

Contribution

It presents an innovative integration of video prediction models with domain-specific data processing and a confidence-based model mixture for Arctic sea ice forecasting.

Findings

Significant accuracy improvements over baseline methods

Effective uncertainty quantification for reliable predictions

Enhanced robustness through confidence-based model combination

Abstract

The increase in Arctic marine activity due to rapid warming and significant sea ice loss necessitates highly reliable, short-term sea ice forecasts to ensure maritime safety and operational efficiency. In this work, we present a novel data-driven approach for sea ice condition forecasting in the Gulf of Ob, leveraging sequences of radar images from Sentinel-1, weather observations, and GLORYS forecasts. Our approach integrates advanced video prediction models, originally developed for vision tasks, with domain-specific data preprocessing and augmentation techniques tailored to the unique challenges of Arctic sea ice dynamics. Central to our methodology is the use of uncertainty quantification to assess the reliability of predictions, ensuring robust decision-making in safety-critical applications. Furthermore, we propose a confidence-based model mixture mechanism that enhances forecast accuracy and model robustness, crucial for reliable operations in volatile Arctic environments. Our results demonstrate substantial improvements over baseline approaches, underscoring the importance of uncertainty quantification and specialized data handling for effective and safe operations and reliable forecasting.