Fighting Fires from Space: Leveraging Vision Transformers for Enhanced Wildfire Detection and Characterization
This work addresses wildfire detection for environmental monitoring and hazard response, but it is incremental as it primarily compares existing methods on a known dataset.
The paper tackles wildfire detection using satellite imagery by comparing Vision Transformers (ViTs) with Convolutional Neural Networks (CNNs), finding that while ViTs can outperform some CNNs by 0.92%, a well-tuned CNN-based UNet achieves the best performance with an IoU of 93.58%, improving over a baseline by 4.58%.
Wildfires are increasing in intensity, frequency, and duration across large parts of the world as a result of anthropogenic climate change. Modern hazard detection and response systems that deal with wildfires are under-equipped for sustained wildfire seasons. Recent work has proved automated wildfire detection using Convolutional Neural Networks (CNNs) trained on satellite imagery are capable of high-accuracy results. However, CNNs are computationally expensive to train and only incorporate local image context. Recently, Vision Transformers (ViTs) have gained popularity for their efficient training and their ability to include both local and global contextual information. In this work, we show that ViT can outperform well-trained and specialized CNNs to detect wildfires on a previously published dataset of LandSat-8 imagery. One of our ViTs outperforms the baseline CNN comparison by 0.92%. However, we find our own implementation of CNN-based UNet to perform best in every category, showing their sustained utility in image tasks. Overall, ViTs are comparably capable in detecting wildfires as CNNs, though well-tuned CNNs are still the best technique for detecting wildfire with our UNet providing an IoU of 93.58%, better than the baseline UNet by some 4.58%.