Burn Severity in Canada's Mountain National Parks: Patterns, Drivers, and Predictions

Abstract

Burn severity refers to the magnitude of fire-induced environmental change, that is, the loss of aboveground and belowground organic matter (Keeley, 2009;Key & Benson, 2006). The term has been used interchangeably with fire severity, but remote sensing applications preferentially use "burn severity" (Keeley, 2009). A comprehensive understanding of burn severity pattern is essential for fire-related ecological research, such as the assessment of post-fire vegetation responses and soil structure changes (e.g.,

Characterizing Topographic Influences of Bushfire Severity Using Machine Learning Models: A Case Study in a Hilly Terrain of Victoria, Australia

“…As reported in different studies, we found that elevation is the topmost variable with significantly higher influence than any other topographic predictors [3], [94], [36]. However, elevation may not be always interpreted independently, because different severity drivers, such as, weather, vegetation composition, fuel availability, moisture, etc.…”

“…RdNBR is the relative version of Differenced Normalised Burn Ratio (dNBR) calculated as per equation (3), where, dNBR is calculated by differencing Normalised Burn Ratio (NBR) of prefire and postfire images as shown in equation (1). In Landsat images, NBR is given by a band combination of near-infrared (NIR), and shortwave-infrared (SWIR) as shown in equation (2).…”

“…A few of them are related to bushfire severity quantification. Most of the ML-based severity research utilises RF model in bushfire severity pattern mapping [23], [42], [45], influencing driver analysis and severity predictive assessment [3], [4], [8], [33], [46]- [49]. In addition, different other models including GB and SVM and their ensembles have demonstrated their capability in explaining complex variable relationships in bushfires applications [50]- [53].…”

“…R EMOTE sensing based bushfire severity assessment provides information on fire-induced vegetation damages by analysing satellite images [1]. Bushfire severity information is mostly used to improve postfire management of vegetation recovery operations [2], [3]. However, understanding potential bushfire severity risks over a landscape prior to fire occurrence is even more critical for effective bushfire mitigation planning [3]- [5].…”

“…Bushfire severity information is mostly used to improve postfire management of vegetation recovery operations [2], [3]. However, understanding potential bushfire severity risks over a landscape prior to fire occurrence is even more critical for effective bushfire mitigation planning [3]- [5]. Nevertheless, bushfire severity prediction requires an improved understanding of the potential drivers and their role in influencing severity patterns over a landscape [1], [6]- [9].…”