Mapping wildfire occurrence at regional scale

Fernández, Juan Ramón de la Riva; Pérez‐Cabello, Fernando; Lana-Renault, Noemí; Koutsias, Nikos

doi:10.1016/j.rse.2004.06.013

Cited by 28 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The location inaccuracy associated with the fire records made it necessary to transform the individual fire events into a continuous variable using kernel density methods. Previous authors (Allgower et al, 2005;Amatulli et al, 2007;de la Riva et al, 2004;Koutsias et al, 2004) found that these methods were suitable to estimate fire density. As a proxy of fire ignition, fire density forms the dependent variable here.…”

Section: Dependent Variablementioning

confidence: 99%

Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest

Oliveira

Oehler

San-Miguel-Ayanz

et al. 2012

Forest Ecology and Management

572

358

View full text Add to dashboard Cite

Section: Dependent Variablementioning

confidence: 99%

Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest

Oliveira

Oehler

San-Miguel-Ayanz

et al. 2012

Forest Ecology and Management

572

358

View full text Add to dashboard Cite

“…A different approach has been based on transformations of the original fire locations to continuous surfaces. Amatulli et al (2006) used latitude and longitude coordinates of fire ignition points provided by the Italian National Fire Database to derive a continuous fire occurrence map through kernel density approach, a method previously used by Koutsias et al (2004) and De la Riva et al (2004). Amatulli et al (2007) recognised that resulting kernel density surfaces might be influenced by the ignition point positions in the highest density zones.…”

Section: Introductionmentioning

confidence: 99%

Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data

2011

View full text Add to dashboard Cite

About 90% of the wildland fires occurred in Southern Europe are caused by human activities. In spite of these figures, the human factor hardly ever appears in the definition of operational fire risk systems due to the difficulty of characterising it. This paper describes two spatially explicit models that predict the probability of fire occurrence due to human causes for their integration into a comprehensive fire risk-mapping methodology. A logistic regression technique at 1 9 1 km grid resolution has been used to obtain these models in the region of Madrid, a highly populated area in the centre of Spain. Socio-economic data were used as predictive variables to spatially represent anthropogenic factors related to fire risk. Historical fire occurrence from 2000 to 2005 was used as the response variable. In order to analyse the effects of the spatial accuracy of the response variable on the model performance (significant variables and classification accuracy), two different models were defined. In the first model, fire ignition points (x, y coordinates) were used as response variable. This model was compared with another one (Kernel model) where the response variable was the density of ignition points and was obtained through a kernel density interpolation technique from fire ignition points randomly located within a 10 9 10 km grid, which is the standard spatial reference unit established by the Spanish Ministry of Environment, Rural and Marine Affairs to report fire location in the national official statistics. Validation of both models was accomplished using an independent set of fire ignition points (years 2006-2007). For the validation, we used the area under the curve (AUC) obtained by a receiver-operating system. The first model performs slightly better with a value of AUC of 0.70 as opposed to 0.67 for the Kernel model. Wildland-urban interface was selected by both models with high relative importance.

show abstract

“…In the boreal forest of Canada the probability of human-caused wildfires increases with dryness and temperature (Pewb and Larsen, 2001;Vega Garcia et al, 1995); these studies developed equations to predict where and when human-caused wildfires would occur by using Geographic Information System (GIS) techniques. Combining historic fire occurrence with human factors, environmental parameters and census statistics, interpolation and overlay were used to locate the uncertain ignition point (de la Riva et al, 2004). Hernandez-Leal et al (2006) defined a risk index and modeled fire probability using Advanced Very High Resolution Radiometer data and the Normalized Difference Vegetation Index.…”

Section: Introductionmentioning

confidence: 99%

Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires

Zhang

Zhou

2010

Journal of Arid Environments

View full text Add to dashboard Cite

Mapping wildfire occurrence at regional scale

Cited by 28 publications

References 5 publications

Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest

Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest

Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data

Using GIS spatial analysis and logistic regression to predict the probabilities of human-caused grassland fires

Contact Info

Product

Resources

About