McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting

TL;DR

McCast introduces a memory-guided latent drift correction method that actively maintains temporal coherence in long-horizon precipitation nowcasting, outperforming existing autoregressive models.

Contribution

The paper proposes a novel Drift-Corrective Memory Bank that explicitly estimates and corrects latent drift, improving long-term forecast reliability.

Findings

Achieves state-of-the-art results on SEVIR and MeteoNet benchmarks.

Significantly improves long-horizon precipitation forecast accuracy.

Produces more temporally coherent and reliable predictions.

Abstract

Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. However, such an approach accumulates errors over long rollouts, causing forecasts to drift away from physically plausible evolution trajectories. Although various studies have attempted to alleviate this problem by improving step-wise prediction accuracy, they largely neglect the global temporal evolution of meteorological systems and lack mechanisms to actively correct drift during rollouts. To address this issue, we propose McCast, a memory-guided latent drift correction method for precipitation nowcasting. Rather than treating memory as an unordered dictionary of latent states for passive conditioning, McCast leverages temporally organized memory to actively correct autoregressive latent evolution. Specifically, McCast introduces a Drift-Corrective Memory Bank (DCBank) that explicitly estimates the temporally consistent drift corrections to calibrate the divergent trajectory. DCBank performs drift correction in two stages: a Corrective Latent Extractor first predicts an initial correction from the current prediction and a reference latent state, and a Correction-Aware Memory Retrieval module then refines the initial correction using temporally organized historical memory. By explicitly correcting latent evolution, instead of improving step-wise prediction accuracy only, McCast produces more temporally coherent and reliable long-horizon forecasts. Experiments on two widely used benchmarks, SEVIR and MeteoNet, show that McCast achieves state-of-the-art performance, particularly in challenging long-horizon forecasting scenarios.