Canadian Forest Service Publications

Integrated fire severity–land cover mapping using very-high-spatial-resolution aerial imagery and point clouds. 2019. Arkin, J., Coops, N.C., Hermosilla, T., Daniels, L.D., Plowright, A. International Journal of Wildland Fire, 28, 840–860.

Year: 2019

Issued by: Pacific Forestry Centre

Catalog ID: 40016

Language: English

Availability: PDF (request by e-mail)

Available from the Journal's Web site.
DOI: 10.1071/WF19008

† This site may require a fee

Mark record

Abstract

Fire severity mapping is conventionally accomplished through the interpretation of aerial photography or the analysis of moderate- to coarse-spatial-resolution pre- and post-fire satellite imagery. Although these methods are well established, there is a demand from both forest managers and fire scientists for higher-spatial-resolution fire severity maps. This study examines the utility of high-spatial-resolution post-fire imagery and digital aerial photogrammetric point clouds acquired from an unmanned aerial vehicle (UAV) to produce integrated fire severity–land cover maps. To accomplish this, a suite of spectral, structural and textural variables was extracted from the UAV-acquired data. Correlation-based feature selection was used to select subsets of variables to be included in random forest classifiers. These classifiers were then used to produce disturbance-based land cover maps at 5- and 1-m spatial resolutions. By analysing maps produced using different variables, the highest-performing spectral, structural and textural variables were identified. The maps were produced with high overall accuracies (5 m, 89.5± 1.4%; 1 m, 85.4± 1.5%), with the 1-m classification produced at slightly lower accuracies. This reduction was attributed to the inclusion of four additional classes, which increased the thematic detail enough to outweigh the differences in accuracy.

Plain Language Summary

Fire severity mapping with remote sensing is conventionally accomplished using moderate to coarse spatial resolution imagery. In this case study, we present methods for mapping fire severity using post-fire high spatial resolution imagery and digital aerial photogrammetric point clouds acquired from an unmanned aerial vehicle. The results reported accuracies of 89.5% and 85.4% at 5-m and 1-m spatial resolution respectively. The automated methods presented and evaluated herein facilitate the immediate production of fire severity maps in a cost effective manner, allowing them to be readily utilized by land managers.