Fractal properties of forest fires in Amazonia as a basis for modelling pan-tropical burnt area
Current methods for modelling burnt area in dynamic global vegetation models (DGVMs) involve complex fire spread calculations, which rely on many inputs, including fuel characteristics, wind speed and countless parameters. They are therefore susceptible to large uncertainties through error propagati...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2014-03-01
|
| Series: | Biogeosciences |
| Online Access: | http://www.biogeosciences.net/11/1449/2014/bg-11-1449-2014.pdf |
| Summary: | Current methods for modelling burnt area in dynamic global vegetation models
(DGVMs) involve complex fire spread calculations, which rely on many inputs,
including fuel characteristics, wind speed and countless parameters. They are
therefore susceptible to large uncertainties through error propagation, but
undeniably useful for modelling specific, small-scale burns. Using observed
fractal distributions of fire scars in Brazilian Amazonia in 2005, we propose
an alternative burnt area model for tropical forests, with fire counts as
sole input and few parameters. This model is intended for predicting
large-scale burnt area rather than looking at individual fire events. A
simple parameterization of a tapered fractal distribution is calibrated at
multiple spatial resolutions using a satellite-derived burnt area map. The
model is capable of accurately reproducing the total area burnt
(16 387 km<sup>2</sup>) and its spatial distribution. When tested pan-tropically
using the MODIS MCD14ML active fire product, the model accurately predicts
temporal and spatial fire trends, but the magnitude of the differences
between these estimates and the GFED3.1 burnt area products varies per
continent. |
|---|---|
| ISSN: | 1726-4170 1726-4189 |