A Data Mining Framework for Forest Fire Mapping

A Data Mining Framework for Forest Fire Mapping

Ahmed Toujani (Silvopastoral Institute of Tabarka, Tunisia & LTSIRS Laboratory, University of Tunis El Manar, Tunisia) and Hammadi Achour (Silvopastoral Institute of Tabarka, Tunisia)
DOI: 10.4018/978-1-5225-0937-0.ch008
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Forest fires constitute the major reasons for the loss of biodiversity and degradation of ecosystems. Locally, forest fires are one of the major natural risks in the Kroumirie mountains, northwestern Tunisia. In these massifs, fires occur frequently, and this requires understanding the complex biophysical parameters of this phenomenon. The special attention of the research is paid to the spatial forecasting of forest fires. Different types of classical frequent itemset algorithms have been tested and employed to reveal forest fire patterns that relate the spatial parameters with the probability of fire occurrence. Extracted frequent patterns are then being aggregated through a defined measurement of pertinence. The forest fire risk zone maps are then generated, resulting in extracted spatial patterns. The experiments showed that, the integration of these patterns into GIS could be advantageous to determine risky places and able to produce good prediction accuracy.
Chapter Preview
Top

Background

Spatial data mining techniques can assist in comprehension and analysis of spatial data, and in exploration of relationships among spatial and non-spatial variables. More specifically, spatial data mining techniques encompass visual analysis, spatial query, characterization and generalization, classification, spatial regression and clustering analysis, detection of spatial and non-spatial association rules besides a wide variety of other fields (Tang & McDonald, 2002).

Conservation planning, precision agriculture, deforestation prevention, resource discovery and various other areas can benefit largely from the extraction of patterns of interest and rules from the spatial data sets like the GIS-data (the data of geographic information system (GIS)) and the remotely sensed imagery (Guo & Mennis, 2009). Spatial Pattern Mining (SPM) is greatly exploited in ecosystem modeling, disaster prevention, forest fire evaluation and other analogous fields. The proposed approach aims to prevent of forest fires with utilizing the spatial data and pattern mining techniques.

Complete Chapter List

Search this Book:
Reset