Mapping forest fires by nonparametric clustering analysis

Abstract

Fires have a noteworthy role to play with regards to ecological and environmental losses in Mediterranean forests. In addition to ecological impacts, fire may create economic, social as well as cultural changes. The detection of fire-scars has critical importance to help decrease losses. In the present study, forest fires recorded in Antalya, one of the most important ecological and tourist regions within the Western Mediterranean, were clustered and mapped. Since the dominant factors and devastation records derived from the cases had nominal-scaled properties, a categorical data-based nonparametric clustering algorithm was performed in this evaluation. The proposed tool, k-modes algorithm, uses modes instead of means for clustering. The algorithm may be implemented quickly and does not make distributional assumptions concerning the available data. It uses a frequency-based method to update the modes of the fires. The derived modes from the maps may be useful information for local authorities to manage. In conclusion, the proposed nonparametric clustering procedure may be employed to build a decision-support system to monitor and identify fire activities and to enhance fire management efficiency.

Keywords

Forest fire / Categorical variable / Clustering / Western mediterranean

References

[1] Aggarwal CC, Reddy CK. Data clustering, algorithms and applications, 2014, Boca Raton: CRC Press.

[2] Aslan YE, Korpeoglu I, Ulusoy Ö. A framework for use of wireless sensor networks in forest fire detection and monitoring. Comput Environ Urban Syst, 2012, 36(6): 614-625.

[3] Boran A, Yorulmaz T (2014) Calculating emissions and economic losses arising from forest fires, a sample district: Antalya, Undergradute thesis, Akdeniz University, Antalya (in Turkish with English abstract)

[4] Bourgeau-Chavez LL, Kasischke ES, Brunzell S, Mudd JP, Tukman M. Mapping fire scars in global boreal forests using imaging radar data. Int J Remote Sens, 2002, 23(20): 4211-4234.

[5] Cere R, Conedera M, Matasci G, Kanevski M, Tonini M, Vega-Orozco C, Volpi M. Wildland-urban interface mapping using multi-temporal landsat imagery: the case of forest fires in Southern Swiss Alps, 2012, Vienna: European Geosciences Union General Assembly.

[6] Chaturvedi A, Green P, Carroll JD. Empirical findings obtained from evaluating k-modes and overlapping k-centroids clustering, 1997, Washington, DC: CSNA Meeting.

[7] Chaturvedi A, Green P, Carroll JD. K-modes clustering. J Classif, 2001, 18: 35-55.

[8] Curovic M, Medarevic M, Pantic D, Spalevic V. Major types of mixed forests of spruce, fir and beech in Montenegro. Austrian J For Sci, 2011, 128(2): 93-111.

[9] Duncan BW, Shao GF, Adrian FW. Delineating a managed fire regime and exploring its relationship to the natural fire regime in East Central Florida, USA: a remote sensing and GIS approach. For Ecol Manage, 2009, 258: 132-145.

[10] Gan GJ, Ma CQ, Wu JH. Data clustering: theory, algorithms, and applications, 2007, Philadelphia: SIAM

[11] Huang ZX. Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Min Knowl Discov, 1998, 2(3): 283-304.

[12] Huang ZX, Ng MK. A fuzzy k-modes algorithm for clustering categorical data. IEEE Trans Fuzzy Syst, 1999, 7(4): 446-452.

[13] Huang ZX, Ng MK. A note on k-modes clustering. J Classif, 2003, 20: 257-261.

[14] Jain A, Dubes R. Algorithms for clustering data, 1988, Englewood Cliffs: Prentice Hall.

[15] Kalabokidis K, Palaiologou P, Gerasopoulos E. Effect of climate change projections on forest fire behavior and values-at-risk in Southwestern Greece. Forests, 2015, 6(6): 2214-2240.

[16] Kaufman L, Rousseeuw P. Finding groups in data—an introduction to cluster analysis, 1990, New York: Wiley.

[17] Mohammadi F, Bavaghar MP, Shabanian N. Forest fire risk zone modeling using logistic regression and GIS: an Iranian case study. Small-scale For, 2014, 13(1): 117-125.

[18] OGM. Progress report, 2014, Ankara: General Directorate of Forestry of Turkey.

[19] OGM-RD. Forest fires in Antalya region, 2015, Antalya: Unpublished Document of Regional Directorate of Forestry.

[20] Omi PN. Forest fires: a reference handbook, 2005, California: ABC-CLIO.

[21] Orozco CV, Tonini M, Conedera M, Kanevski M. Cluster recognition in spatial-temporal sequences: the case of forest fires. Geoinformatica, 2012, 16: 653-673.

[22] Pereira MG, Caramelo L, Orozco CV, Costa R, Tonini M. Space-time clustering analysis performance of an aggregated dataset: the case of wildfires in Portugal. Environ Model Softw, 2015, 72: 239-249.

[23] Perona G, Brebbia CA. Modelling, monitoring and management of forest fires II, 2010, Southampton: WIT Press

[24] Pourghasemi HR. GIS-based forest fire susceptibility mapping in Iran: a comparison between evidential belief function and binary logistic regression models. Scand J For Res, 2016, 31(1): 80-98.

[25] Shao GF, Duncan BW. Effects of band combinations and GIS masking on fire scar mapping at local scales in east-central Florida, USA. Can J Remote Sens, 2007, 33: 250-259.

[26] Sunar F, Özkan C. Forest fire analysis with remote sensing data. Int J Remote Sens, 2001, 22(12): 2265-2277.

[27] Tonini M, Tuia D, Ratle F. Detection of clusters using space-time scan statistics. Wildland Fire, 2009, 18(7): 830-836.

[28] Tuia D, Lasaponara R, Telesca L, Kanevski M. Identifying spatial clustering phenomena in forest-fire sequences. Phys A, 2007, 376(1): 596-600.

[29] Yang W, Gardelin M, Olsson J. Multi-variable bias correction: application of forest fire risk in present and future climate in Sweden. Nat Hazards Earth Syst Sci, 2015, 15(9): 2037-2057.