Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Determination of Multi-Spectral Band Utility for Mapping Wildland Fire Burn Extent and Severity

Version 1 : Received: 1 May 2023 / Approved: 2 May 2023 / Online: 2 May 2023 (02:23:31 CEST)

How to cite: McCall, C.; Hamilton, D. Determination of Multi-Spectral Band Utility for Mapping Wildland Fire Burn Extent and Severity. Preprints 2023, 2023050042. https://doi.org/10.20944/preprints202305.0042.v1 McCall, C.; Hamilton, D. Determination of Multi-Spectral Band Utility for Mapping Wildland Fire Burn Extent and Severity. Preprints 2023, 2023050042. https://doi.org/10.20944/preprints202305.0042.v1

Abstract

Through the use of machine learning algorithms like the Support Vector Machine, it has been show that burn extent can be accurately mapped from hyperspatial drone imagery in both grasslands and forests. Despite these successes, hyperspatial imagery must be acquired via drones, requiring large amounts of time and resources to capture areas much smaller than the large catastrophic fires which result in the majority of the lands burned each year by wildland fires. To overcome this difficulty, high spatial resolution satellite imagery from Worldview2 can be substituted for hyperspatial drone imagery, allowing for larger regions of images to be acquired more easily and efficiently. Additionally, Worldview2 trades spatial resolution for spectral resolution and extent, capturing images in 8 multispectral bands as opposed to 3 band imagery in the visible spectra. This research examines the utility of each of the 8 bands observed in Worldview2 imagery using an Iterative Dichotomiser 3 decision tree, then uses these bands to map burn extent and biomass consumption. Several classifications of burn extent and biomass consumption are produced and compared based on the bands used as inputs. The results show that using Worldview2 imagery to map burn extent and biomass consumption results in highly accurate maps, with slight improvements when additional bands are added.

Keywords

Support Vector Machine (SVM); Worldview2; Satellite Imagery; Iterative Dichotomiser 3 (ID3); Burn Extent; Burn Severity; Biomass Consumption

Subject

Environmental and Earth Sciences, Remote Sensing

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.