Burned Area Mapping in the Brazilian Savanna Using a One-Class Support Vector Machine Trained by Active Fires

We used the Visible Infrared Imaging Radiometer Suite (VIIRS) active fire data (375 m spatial resolution) to automatically extract multispectral samples and train a One-Class Support Vector Machine for burned area mapping, and applied the resulting classification algorithm to 300-m spatial resolutio...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 9; no. 11; p. 1161
Main Authors Pereira, Allan, Pereira, José, Libonati, Renata, Oom, Duarte, Setzer, Alberto, Morelli, Fabiano, Machado-Silva, Fausto, de Carvalho, Luis
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.11.2017
Subjects
active fire
Algorithms
Autonomy
burned area
Cerrado
Fires
First aid
Image classification
Infrared imaging
Infrared radiometers
Landsat
Landsat satellites
Mapping
MODIS
PROBA-V
Radiometry
Reflectance
Remote sensing
Satellite imagery
Savannahs
Scars
Spatial data
Spatial discrimination
Spatial resolution
support vector machine one class
VIIRS
Online AccessGet full text

Cover

More Information
Summary:We used the Visible Infrared Imaging Radiometer Suite (VIIRS) active fire data (375 m spatial resolution) to automatically extract multispectral samples and train a One-Class Support Vector Machine for burned area mapping, and applied the resulting classification algorithm to 300-m spatial resolution imagery from the Project for On-Board Autonomy-Vegetation (PROBA-V). The active fire data were screened to prevent extraction of unrepresentative burned area samples and combined with surface reflectance bi-weekly composites to produce burned area maps. The procedure was applied over the Brazilian Cerrado savanna, validated with reference maps obtained from Landsat images and compared with the Collection 6 Moderate Resolution Imaging Spectrometer (MODIS) Burned Area product (MCD64A1) Results show that the algorithm developed improved the detection of small-sized scars and displayed results more similar to the reference data than MCD64A1. Unlike active fire-based region growing algorithms, the proposed approach allows for the detection and mapping of burn scars without active fires, thus eliminating a potential source of omission error. The burned area mapping approach presented here should facilitate the development of operational-automated burned area algorithms, and is very straightforward for implementation with other sensors.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs9111161