Increasing Spatial Detail of Burned Scar Maps Using IRS-AWiFS Data for Mediterranean Europe

Abstract: A two stage burned scar detection approach is applied to produce a burned scar map for Mediterranean Europe using IRS-AWiFS imagery acquired at the end of the 2009 fire season. The first stage identified burned scar seeds based on a learning algorithm (Artificial Neural Network) coupled with a bootstrap aggregation process. The second stage implemented a region growing process to extend the area of the burned scars. Several ancillary datasets were used for the accuracy assessment and a final visual check was performed to refine the burned scar product. Training data for the learning algorithm were obtained from MODIS-based polygons, which were generated by the Rapid Damage Assessment module of the European Forest Fire Information System. The map produced from this research is the first attempt to increase the spatial detail of current burned scar maps for the Mediterranean region. The map has been analyzed and compared to existing burned area polygons from the European Forest Fire Information System. The comparison showed that the IRS-AWiFS-based burned scar map improved the delineation of burn scars; in addition the process identified a number of small burned scars that were not detected on lower resolution sensor data. Nonetheless, the results do not clearly support the improved capability for the detection of smaller burned scars. A number of reasons can be provided for the under-detection of burned scars, these include: the lack of a full coverage and cloud free imagery, the time lag between forest fires and image acquisition date and the occurrence of fires after the image acquisition dates. On the other hand, the limited

[1]  E. Chuvieco,et al.  Mapping and inventory of forest fires from digital processing of tm data , 1988 .

[2]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[3]  J. Grégoire,et al.  The GBA2000 initiative: Developing a global burnt area database from SPOT-VEGETATION imagery , 2003 .

[4]  Michael T. Manry,et al.  Attributes of neural networks for extracting continuous vegetation variables from optical and radar , 1998 .

[5]  Ruiliang Pu,et al.  Determination of Burnt Scars Using Logistic Regression and Neural Network Techniques from a Single Post-Fire Landsat-7 ETM+ Image , 2004 .

[6]  Camia Andrea,et al.  Forest Fires at a Glance: Facts, Figures and Trends in the EU , 2009 .

[7]  Aitor Bastarrika Izaguirre.  Cartografía automática de área quemada a nivel local-regional mediante algoritmos de contexto espacial , 2009 .

[8]  M. Isabel.  Cartografia e inventario de incendios forestales en la peninsula iberica a partir de imagenes noaa-avhrr , 1999 .

[9]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[10]  Peter Vogt,et al.  A cloud mask methodology for high resolution remote sensing data combining information from high and medium resolution optical sensors , 2011 .

[11]  Jaime Esper,et al.  Trends and Visions for Small Satellite Missions , 2008 .

[12]  Thomas A. Hennig,et al.  The Shuttle Radar Topography Mission , 2001, Digital Earth Moving.

[13]  Peter Strobl,et al.  Forest Fires in the European Mediterranean Region: Mapping and Analysis of Burned Areas , 2009 .

[14]  Peter Vogt,et al.  Towards a pan-European burnt scar mapping methodology based on single date medium resolution optical remote sensing data , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[15]  Jose L. Casanova,et al.  Burned area mapping system and fire detection system, based on neural networks and NOAA-AVHRR imagery , 2001 .

[16]  C. Justice,et al.  An examination of spectral band ratioing to reduce the topographic effect on remotely sensed data , 1981 .

[17]  D. Roy,et al.  Burned area mapping using multi-temporal moderate spatial resolution data—a bi-directional reflectance model-based expectation approach , 2002 .

[18]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[19]  G. Perry,et al.  Monthly burned area and forest fire carbon emission estimates for the Russian Federation from SPOT VGT , 2003 .

[20]  David P. Roy,et al.  Land Use and Fires , 2012 .

[21]  Ioannis Z. Gitas,et al.  Burned Area Mapping in Greece Using SPOT-4 HRVIR Images and Object-Based Image Analysis , 2012, Remote. Sens..

[22]  Ashutosh Kumar Singh,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2010 .

[23]  D. Roy,et al.  The collection 5 MODIS burned area product — Global evaluation by comparison with the MODIS active fire product , 2008 .

[24]  Will Steffen,et al.  Establishing A Earth Observation Product Service For The Terrestrial Carbon Community: The Globcarbon Initiative , 2006 .

[25]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[26]  '. EmilioChuvieco,et al.  Using Cluster Analysis to Improve the Selection of Training Statistics in Classifying Remotely Sensed Data , 2008 .

[27]  Y. Birot.  Living with wildfires: what science can tell us - a contribution to the science-policy dialogue. , 2009 .

[28]  M. Cochrane.  Linear mixture model classification of burned forests in the Eastern Amazon , 1998 .

[29]  J. Cihlar,et al.  Hotspot and NDVI Differencing Synergy (HANDS): A New Technique for Burned Area Mapping over Boreal Forest , 2000 .

[30]  J. Pereira,et al.  Vegetation burning in the year 2000: Global burned area estimates from SPOT VEGETATION data , 2004 .

[31]  Charalambos Kontoes,et al.  A comparative analysis of a fixed thresholding vs. a classification tree approach for operational burn scar detection and mapping , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[32]  Pieter Kempeneers,et al.  Data Fusion of Different Spatial Resolution Remote Sensing Images Applied to Forest-Type Mapping , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[33]  George P. Petropoulos,et al.  Burnt area delineation from a uni-temporal perspective based on Landsat TM imagery classification using Support Vector Machines , 2011, Int. J. Appl. Earth Obs. Geoinformation.

[34]  P. Mausel,et al.  Assessment of vegetation change in a fire-altered forest landscape. , 1990 .

[35]  S. Plummer,et al.  Burnt area detection at global scale using ATSR‐2: The GLOBSCAR products and their qualification , 2004 .

[36]  Ignazio Gallo,et al.  Mapping burned surfaces in Sub-Saharan Africa based on multi-temporal neural classification , 2003 .

[37]  F. Gonzalez-Alonso,et al.  Integration of AWiFS and MODIS active fire data for burn mapping at regional level using the Burned Area Synergic Algorithm (BASA) , 2009 .

[38]  David P. Roy,et al.  Southern Africa Validation of the MODIS, L3JRC, and GlobCarbon Burned-Area Products , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[39]  E. Chuvieco,et al.  Mapping burned areas from Landsat TM/ETM+ data with a two-phase algorithm: Balancing omission and commission errors , 2011 .

[40]  F. Sunar,et al.  Forest fire analysis with remote sensing data , 2001 .