TeleViT: Teleconnection-driven Transformers Improve Subseasonal to Seasonal Wildfire Forecasting
This work addresses the problem of long-term wildfire forecasting for resource planning and mitigation, offering a novel deep learning approach that improves accuracy in capturing Earth system dynamics.
The paper tackled subseasonal to seasonal wildfire forecasting by proposing TeleViT, a teleconnection-driven vision transformer that integrates local and global inputs to treat the Earth as an interconnected system, achieving accurate predictions of global burned area patterns up to four months in advance with gains especially pronounced in larger forecasting windows.
Wildfires are increasingly exacerbated as a result of climate change, necessitating advanced proactive measures for effective mitigation. It is important to forecast wildfires weeks and months in advance to plan forest fuel management, resource procurement and allocation. To achieve such accurate long-term forecasts at a global scale, it is crucial to employ models that account for the Earth system's inherent spatio-temporal interactions, such as memory effects and teleconnections. We propose a teleconnection-driven vision transformer (TeleViT), capable of treating the Earth as one interconnected system, integrating fine-grained local-scale inputs with global-scale inputs, such as climate indices and coarse-grained global variables. Through comprehensive experimentation, we demonstrate the superiority of TeleViT in accurately predicting global burned area patterns for various forecasting windows, up to four months in advance. The gain is especially pronounced in larger forecasting windows, demonstrating the improved ability of deep learning models that exploit teleconnections to capture Earth system dynamics. Code available at https://github.com/Orion-Ai-Lab/TeleViT.