Detection of Tornado damage in forested regions via convolutional neural networks and uncrewed aerial system photogrammetry

Disaster damage assessments are a critical component to response and recovery operations. In recent years, the field of remote sensing has seen innovations in automated damage assessments and uncrewed aerial system (UAS) collection capabilities. However, little work has been done to explore the intersection of automated methods and UAS photogrammetry to detect tornado damage. UAS imagery, combined with structure from motion (SfM) output, can directly be used to train models to detect tornado damage. In this research, we trained a convolutional neural network (CNN) that can classify tornado damage in forests using SfM-derived orthophotos and digital surface models. The findings indicate that a CNN approach provides a higher accuracy than random forest classification and that digital surface model (DSM)-based derivatives—especially the vertically exaggerated multi-directional shaded relief model and vector ruggedness measure—add significant predictive value over the use of the orthophoto mosaic alone. This method has the potential to fill a gap in tornado damage assessment, as tornadoes that occur in wooded areas are typically difficult to survey on the ground and in the field; an improved record of tornado damage in these areas will improve our understanding of tornado climatology.