Burnt area mapping using Support Vector Machines

Zammit, Olivier; Descombes, Xavier; Zerubia, Josiane

doi:10.1016/j.foreco.2006.08.269

Cited by 23 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high frequency of fires is a natural and recurrent element in the Mediterranean region and has been closely linked to the climatic conditions that dominate in these areas, characterised by prolonged drought periods generating favourable conditions for fire outbreaks (Cuomo et al, 2001;Zammit et al, 2006). Obtaining accurate as well as rapid mapping of burnt areas from a wildfire, is of key importance to environmental scientists and policy makers.…”

Section: Introductionmentioning

confidence: 99%

“…SVM classifiers are also easy to implement, since only a few parameters need to be adjusted by the user (Karimi et al, 2006) and they have shown to generally provide good results when small training sets are used (Pal and Mather, 2006). SVM has been widely applied in many classification problems using remote sensing data (Brown et al, 1999;Zhu and Blumberg, 2002;Keuchel et al, 2003;Sanchez-Hernandez et al, 2007;Tseng et al, 2008;Koetz et al, 2008;Kavzoglu and Colkesen, 2009), including burnt area mapping implemented in SPOT5 multispectral data (Zammit et al, 2006).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective post-fire assessment: a case study from the Greek wildland fires of 2007

Petropoulos

Knorr

Scholze

et al. 2010

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Remote sensing is increasingly being used as a cost-effective and practical solution for the rapid evaluation of impacts from wildland fires. The present study investigates the use of the support vector machine (SVM) classification method with multispectral data from the Advanced Spectral Emission and Reflection Radiometer (ASTER) for obtaining a rapid and cost effective post-fire assessment in a Mediterranean setting. A further objective is to perform a detailed intercomparison of available burnt area datasets for one of the most catastrophic forest fire events that occurred near the Greek capital during the summer of 2007. For this purpose, two ASTER scenes were acquired, one before and one closely after the fire episode. Cartography of the burnt area was obtained by classifying each multiband ASTER image into a number of discrete classes using the SVM classifier supported by land use/cover information from the CORINE 2000 land nomenclature. Overall verification of the derived thematic maps based on the classification statistics yielded results with a mean overall accuracy of 94.6% and a mean Kappa coefficient of 0.93. In addition, the burnt area estimate derived from the post-fire ASTER image was found to have an average difference of 9.63% from those reported by other operationally-offered burnt area datasets available for the test region.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective post-fire assessment: a case study from the Greek wildland fires of 2007

Petropoulos

Knorr

Scholze

et al. 2010

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

show abstract

“…Classifications in this study were performed using the SVM classifier, which is widely applied in the field of pattern recognition in the last few years [24]. In its original form, SVM is a binary classifier, which finds the optimal separating hyperplane between two classes [35].…”

Section: Step 4: Svm Pixel and Object-based Classification Modelsmentioning

confidence: 99%

“…Up until now, several classification techniques have been applied in burned area mapping, including maximum likelihood classification [13,14], logistic regression [15], classification and regression trees [14,16] linear and/or nonlinear spectral mixture analysis [17,18], thresholding of Vegetation Indices (VIs) [14,19], Neural Networks [20], Neuro-Fuzzy techniques [21], Support Vector Machines (SVMs) [22][23][24], and Object Based Image Analysis (OBIA) [25,26]. However, the selection of the optimal method each time depends on several factors, such as the scale and the goals of the current project.…”

Section: Introductionmentioning

confidence: 99%

Burned Area Mapping Using Support Vector Machines and the FuzCoC Feature Selection Method on VHR IKONOS Imagery

et al. 2014

View full text Add to dashboard Cite

Abstract:The ever increasing need for accurate burned area mapping has led to a number of studies that focus on improving the mapping accuracy and effectiveness. In this work, we investigate the influence of derivative spectral and spatial features on accurately mapping recently burned areas using VHR IKONOS imagery. Our analysis considers both pixel and object-based approaches, using two advanced image analysis techniques: (a) an efficient feature selection method based on the Fuzzy Complementary Criterion (FuzCoC) and (b) the Support Vector Machine (SVM) classifier. In both cases (pixel and object-based), a number of higher-order spectral and spatial features were produced from the original image. The proposed methodology was tested in areas of Greece recently affected by severe forest fires, namely, Parnitha and Rhodes. The extensive comparative analysis indicates that the SVM object-based scheme exhibits higher classification accuracy than the respective pixel-based one. Additionally, the accuracy increased with the addition of derivative features and subsequent implementation of the FuzCoC feature selection (FS) method. Apart from the positive effect in the classification accuracy, the application of the FuzCoC FS method significantly reduces the computational requirements and facilitates the manipulation of the large data volume. In both cases (pixel and objet) the results confirmed that the use of an efficient feature selection method is a prerequisite step when extra information through OPEN ACCESS Remote Sens. 2014, 6 12006 higher-order features is added to the classification process of VHR imagery for burned area mapping.

show abstract

“…In the Mediterranean region in particular, fire is a natural and recurrent element, as 90 % of all wildland fires take place every year in those areas (Rosa et al, 2008). The high frequency of fires in the Mediterranean has been closely linked to the climatic conditions that dominate in these areas, characterised by prolonged drought periods generating favourable conditions for fire outbreaks (Cuomo et al, 2001;Zammit et al, 2006). In addition, the climate change, along with the effects of various anthropogenic activities, further increase the risk of fire occurrence and thus the damage caused to both nature and economy (Boboulos and Purvis, 2009).…”

Section: Introductionmentioning

confidence: 99%

An intercomparison of burnt area estimates derived from key operational products: the Greek wildland fires of 2005–2007

Kalivas

Petropoulos

Athanasiou

et al. 2013

Nonlin. Processes Geophys.

View full text Add to dashboard Cite

With the support of new technologies such as of remote sensing, today's societies have been able to map and analyse wildland fires at large observational scales. With regards to burnt area mapping in particular, two of the most widely used operational products are offered today by the United States National Aeronautics and Space Administration (NASA) and the European Forest Fires Information System (EFFIS) of the European Commission. In this study, a rigorous intercomparison of the burnt area estimates derived by these two products is performed in a geographical information system (GIS) environment for the Greek fires that occurred from 2005 to 2007. For the same temporal interval, the relationships of the burnt area estimates by each product are examined with respect to land use/cover and elevation derived from CORINE 2000 and the ASTER global digital elevation model (GDEM), respectively. Generally, noticeable differences were found in the burnt area estimates by the two products both spatially and in absolute numbers. The main findings are described and the differences in the burnt area estimates between the two operational datasets are discussed. The lack of precise agreement between the two products which was found does not necessarily mean that one or the other product is inaccurate. Rather, it underlines the requirement for their calibration and validation using high-resolution remote sensing data in future studies. Our work not only builds upon a series of analogous studies evaluating the accuracy of the same or similar operational products worldwide, but also contributes towards the development of standardised validation methodologies required in objectively evaluating such datasets

show abstract

Burnt area mapping using Support Vector Machines

Cited by 23 publications

References 8 publications

Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective post-fire assessment: a case study from the Greek wildland fires of 2007

Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective post-fire assessment: a case study from the Greek wildland fires of 2007

Burned Area Mapping Using Support Vector Machines and the FuzCoC Feature Selection Method on VHR IKONOS Imagery

An intercomparison of burnt area estimates derived from key operational products: the Greek wildland fires of 2005–2007

Contact Info

Product

Resources

About