Surrogate Modelling for Sea Ice Concentration using Lightweight Neural Ensemble

TL;DR

This paper introduces LANE-SI, a lightweight neural ensemble model that effectively forecasts sea ice concentration, offering comparable or superior accuracy to traditional physical models, with significant improvements in the Kara Sea.

Contribution

The paper presents a novel adaptive surrogate modeling approach using lightweight neural ensembles for sea ice forecasting, outperforming existing physics-based systems in specific regions.

Findings

20% improvement over SEAS5 in the Kara Sea

Forecast accuracy comparable to resource-intensive physical models

Effective long-term sea ice concentration predictions

Abstract

The modeling and forecasting of sea ice conditions in the Arctic region are important tasks for ship routing, offshore oil production, and environmental monitoring. We propose the adaptive surrogate modeling approach named LANE-SI (Lightweight Automated Neural Ensembling for Sea Ice) that uses ensemble of relatively simple deep learning models with different loss functions for forecasting of spatial distribution for sea ice concentration in the specified water area. Experimental studies confirm the quality of a long-term forecast based on a deep learning model fitted to the specific water area is comparable to resource-intensive physical modeling, and for some periods of the year, it is superior. We achieved a 20% improvement against the state-of-the-art physics-based forecast system SEAS5 for the Kara Sea.