Masked Autoregressive Model for Weather Forecasting

TL;DR

This paper introduces MAM4WF, a masked autoregressive model that improves long-term weather forecasting by learning robust spatiotemporal relationships, outperforming traditional methods across multiple datasets.

Contribution

The paper presents a novel masked autoregressive approach that combines autoregressive and lead time embedding techniques for enhanced weather prediction.

Findings

Superior performance on five weather and climate datasets

Effective modeling of long-term atmospheric correlations

Robust reconstruction of missing spatiotemporal data

Abstract

The growing impact of global climate change amplifies the need for accurate and reliable weather forecasting. Traditional autoregressive approaches, while effective for temporal modeling, suffer from error accumulation in long-term prediction tasks. The lead time embedding method has been suggested to address this issue, but it struggles to maintain crucial correlations in atmospheric events. To overcome these challenges, we propose the Masked Autoregressive Model for Weather Forecasting (MAM4WF). This model leverages masked modeling, where portions of the input data are masked during training, allowing the model to learn robust spatiotemporal relationships by reconstructing the missing information. MAM4WF combines the advantages of both autoregressive and lead time embedding methods, offering flexibility in lead time modeling while iteratively integrating predictions. We evaluate MAM4WF across weather, climate forecasting, and video frame prediction datasets, demonstrating superior performance on five test datasets.