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

• Published in: Remote 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
• Language: English
• 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

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...