ARE HIGH SEVERITY FIRES INCREASING IN SOUTHERN AUSTRALIA (original) (raw)

Evaluation of Spectral Indices for Assessing Fire Severity in Australian Temperate Forests

Remote Sensing, 2018

Spectral indices derived from optical remote sensing data have been widely used for fire-severity classification in forests from local to global scales. However, comparative analyses of multiple indices across diverse forest types are few. This represents an information gap for fire management agencies in areas like temperate southeastern Australia, which is characterised by a diversity of natural forests that vary in structure, and in the fire-regeneration strategies of the dominant trees. We evaluate 10 spectral indices across eight areas burnt by wildfires in 1998, 2006, 2007, and 2009 in southeastern Australia. These wildfire areas encompass 13 forest types, which represent 86% of the 7.9M ha region's forest area. Forest types were aggregated into six forest groups based on their fire-regeneration strategies (seeders, resprouters) and structure (tree height and canopy cover). Index performance was evaluated for each forest type and forest group by examining its sensitivity to four fire-severity classes (unburnt, low, moderate, high) using three independent methods (anova, separability, and optimality). For the best-performing indices, we calculated index-specific thresholds (by forest types and groups) to separate between the four severity classes, and evaluated the accuracy of fire-severity classification on independent samples. Our results indicated that the best-performing indices of fire severity varied with forest type and group. Overall accuracy for the best-performing indices ranged from 0.50 to 0.78, and kappa values ranged from 0.33 (fair agreement) to 0.77 (substantial agreement), depending on the forest group and index. Fire severity in resprouter open forests and woodlands was most accurately mapped using the delta Normalised Burnt ratio (dNBR). In contrast, dNDVI (delta Normalised difference vegetation index) performed best for open forests with mixed fire responses (resprouters and seeders), and dNDWI (delta Normalised difference water index) was the most accurate for obligate seeder closed forests. Our analysis highlighted the low sensitivity of all indices to fire impacts in Rainforest. We conclude that the optimal spectral index for quantifying fire severity varies with forest type, but that there is scope to group forests by structure and fire-regeneration strategy to simplify fire-severity classification in heterogeneous forest landscapes.

Fire-severity classification across temperate Australian forests: random forests versus spectral index thresholding Fire-severity classification across temperate Australian forests: random forests versus spectral index thresholding

SPIE Remote Sensing, 2019, Strasbourg, France, 2016

Machine learning and spectral index (SI) thresholding approaches have been tested for fire-severity mapping from local to regional scales in a range of forest types worldwide. While index thresholding can be easily implemented, its operational utility over large areas is limited as the optimum index may vary with forest type and fire regimes. In contrast, machine learning algorithms allow for multivariate fire classifications. This study compared the accuracy of fire-severity classifications from SI thresholding with those from Random Forests (RF). Reference data were from 3730 plots within the boundaries of eight major wildfires across the six temperate forest 'functional' groups of Victoria, southeastern Australia. The reference plots were randomly divided into training and validation datasets (60/40) for each fire-severity class (unburnt, low, moderate, high) and forest functional group. SI fire-severity classifications were conducted using thresholds derived in a previous study based on the same datasets. A RF classification algorithm was trained to derive fire-severity levels based on appropriate spectral indices and their temporal difference. The RF classification outperformed the SI thresholding approach in most cases, increasing overall accuracy by 11% on a forest-group basis, and 16% on an individual wildfire basis. Adding more predictor variables into the RF algorithm did not improve classification accuracy. Greater overall accuracies (by 12% on average) were achieved when in situ data (rather than data from other fires) were used to train the RF algorithm. Our study shows the utility of Random Forest algorithms for streamlining fire-severity mapping across heterogeneous forested landscapes.

The development of an automated algorithm to map fire severity from satellite imagery: tropical savannas northern Australia

2011

Fire severity is the post-fire effect of fire on the vegetation. The fire severity mapping algorithm developed in this study correlated helicopter-based spectra collected over a site using a hand held spectrometer and ground data describing the fire severity within the spectrometer field of view. The differenced Normalized Burn Ratio (∆NBR) quite clearly distinguished between severe and not-severe fires (r 2 = 0.94). However, further discrimination into three or more classes required the development of other indices incorporating the region of the spectrum represented by MODIS band 6 (1628-1652 nm). This poses problems operationally as band 6 on Aqua is dysfunctional thus halving the available data.

Fire-severity classification across temperate Australian forests: random forests versus spectral index thresholding

SPIE Remote Sensing, 2019, Strasbourg, France, 2019

Machine learning and spectral index (SI) thresholding approaches have been tested for fire-severity mapping from local to regional scales in a range of forest types worldwide. While index thresholding can be easily implemented, its operational utility over large areas is limited as the optimum index may vary with forest type and fire regimes. In contrast, machine learning algorithms allow for multivariate fire classifications. This study compared the accuracy of fire-severity classifications from SI thresholding with those from Random Forests (RF). Reference data were from 3730 plots within the boundaries of eight major wildfires across the six temperate forest 'functional' groups of Victoria, southeastern Australia. The reference plots were randomly divided into training and validation datasets (60/40) for each fire-severity class (unburnt, low, moderate, high) and forest functional group. SI fire-severity classifications were conducted using thresholds derived in a previous study based on the same datasets. A RF classification algorithm was trained to derive fire-severity levels based on appropriate spectral indices and their temporal difference. The RF classification outperformed the SI thresholding approach in most cases, increasing overall accuracy by 11% on a forest-group basis, and 16% on an individual wildfire basis. Adding more predictor variables into the RF algorithm did not improve classification accuracy. Greater overall accuracies (by 12% on average) were achieved when in situ data (rather than data from other fires) were used to train the RF algorithm. Our study shows the utility of Random Forest algorithms for streamlining fire-severity mapping across heterogeneous forested landscapes.