TeleViT1.0: Teleconnection-aware Vision Transformers for Subseasonal to Seasonal Wildfire Pattern Forecasts

TL;DR

This paper introduces TeleViT, a novel vision transformer model that incorporates global teleconnection data for improved wildfire prediction up to four months ahead, demonstrating significant performance gains over existing models.

Contribution

The paper presents a multi-scale, teleconnection-aware transformer architecture that effectively fuses local, global, and teleconnection information for long-term wildfire forecasting.

Findings

TeleViT outperforms U-Net++, ViT, and climatology in AUPRC across all lead times.

Global inputs and indices help maintain high prediction skill up to four months.

The model shows highest accuracy in seasonally consistent fire regimes.

Abstract

Forecasting wildfires weeks to months in advance is difficult, yet crucial for planning fuel treatments and allocating resources. While short-term predictions typically rely on local weather conditions, long-term forecasting requires accounting for the Earth's interconnectedness, including global patterns and teleconnections. We introduce TeleViT, a Teleconnection-aware Vision Transformer that integrates (i) fine-scale local fire drivers, (ii) coarsened global fields, and (iii) teleconnection indices. This multi-scale fusion is achieved through an asymmetric tokenization strategy that produces heterogeneous tokens processed jointly by a transformer encoder, followed by a decoder that preserves spatial structure by mapping local tokens to their corresponding prediction patches. Using the global SeasFire dataset (2001-2021, 8-day resolution), TeleViT improves AUPRC performance over U-Net++, ViT, and climatology across all lead times, including horizons up to four months. At zero lead, TeleViT with indices and global inputs reaches AUPRC 0.630 (ViT 0.617, U-Net 0.620), at 16x8day lead (around 4 months), TeleViT variants using global input maintain 0.601-0.603 (ViT 0.582, U-Net 0.578), while surpassing the climatology (0.572) at all lead times. Regional results show the highest skill in seasonally consistent fire regimes, such as African savannas, and lower skill in boreal and arid regions. Attention and attribution analyses indicate that predictions rely mainly on local tokens, with global fields and indices contributing coarse contextual information. These findings suggest that architectures explicitly encoding large-scale Earth-system context can extend wildfire predictability on subseasonal-to-seasonal timescales.