Multispectral and LiDAR data fusion for fuel type mapping using Support Vector Machine and decision rules

Garcia-Alonso, M, Riano, D, Chuvieco, E, Salas, J and Danson, FM ORCID: 2011, 'Multispectral and LiDAR data fusion for fuel type mapping using Support Vector Machine and decision rules' , Remote Sensing of Environment, 115 (6) , pp. 1369-1379.

[img] PDF - Published Version
Restricted to Repository staff only

Download (1MB) | Request a copy


This paper presents a method for mapping fuel types using previous termLiDARnext term and previous termmultispectralnext termprevious termdatanext term. A two-phase classification method is proposed to discriminate the fuel classes of the Prometheus classification system, which is adapted to the ecological characteristics of the European Mediterranean basin. The first step mapped the main fuel groups, namely grass, shrub and tree, as well as non-fuel classes. This phase was carried out using a Support Vector Machine (SVM) classification combining previous termLiDARnext term and previous ermmultispectralnext termprevious termdatanext term. The overall accuracy of this classification was 92.8% with a kappa coefficient of 0.9. The second phase of the proposed method focused on discriminating additional fuel categories based on vertical information provided by the previous termLiDARnext term measurements. Decision rules were applied to the output of the SVM classification based on the mean height of previous termLiDARnext term returns and the vertical distribution of fuels, described by the relative previous termLiDARnext term point density in different height intervals. The final fuel type classification yielded an overall accuracy of 88.24% with a kappa coefficient of 0.86. Some confusion was observed between fuel types 7 (dense tree cover presenting vertical continuity with understory vegetation) and 5 (trees with less than 30% of shrub cover) in some areas covered by Holm oak, which showed low previous termLiDARnext term pulses penetration so that the understory vegetation was not correctly sampled.

Item Type: Article
Themes: Subjects outside of the University Themes
Schools: Schools > School of Environment and Life Sciences > Ecosystems and Environment Research Centre
Journal or Publication Title: Remote Sensing of Environment
Publisher: Elsevier
Refereed: Yes
ISSN: 0034-4257
Funders: Natural Environment Research Council (NERC)
Depositing User: FM Danson
Date Deposited: 28 Sep 2011 10:47
Last Modified: 16 Feb 2022 12:30

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)