Pixel and object-based classification approaches for mapping forest fuel types in Tenerife Island from ASTER data
Alfonso Alonso-Benito A C , Lara A. Arroyo B , Manuel Arbelo A , Pedro Hernández-Leal A and Alejandro González-Calvo A
+ Author Affiliations
- Author Affiliations
A Grupo de Observación de la Tierra y la Atmósfera (GOTA), Departamento de Física FEES, Universidad de La Laguna, E-38206 La Laguna (S/C Tenerife), Spain.
B Centre for Human and Social Sciences, Spanish Council for Scientific Research, Albasanz 26-28, E-28037 Madrid, Spain.
C Corresponding author. Email: aaloben@ull.es
International Journal of Wildland Fire 22(3) 306-317 https://doi.org/10.1071/WF11068
Submitted: 13 May 2011 Accepted: 16 July 2012 Published: 3 October 2012
Abstract
Four classification algorithms have been assessed and compared with mapped forest fuel types from Terra-ASTER sensor images in a representative area of Tenerife Island (Canary Islands, Spain). A BEHAVE fuel-type map from 2002, together with field data also obtained in 2002 during the Third Spanish National Forest Inventory, was used as reference data. The BEHAVE fuel types of the reference dataset were first converted into the Fire Behaviour Fuel Types described by Scott and Burgan, taking into account the vegetation of the study area. Then, three pixel-based algorithms (Maximum Likelihood, Neural Network and Support Vector Machine) and an Object-Based Image Analysis were applied to classify the Scott and Burgan fire behaviour fuel types from an ASTER image from 3 March 2003. The performance of the algorithms tested was assessed and compared in terms of quantity disagreement and allocation disagreement. Within the pixel-based classifications, the best results were obtained from the Support Vector Machine algorithm, which showed an overall accuracy of 83%; 14% of disagreement was due to allocation and 3% to quantity disagreement. The Object-Based Image Analysis approach produced the most accurate maps, with an overall accuracy of 95%; 4% disagreement was due to allocation and 1% to quantity disagreement. The object-based classification achieved thus an overall accuracy of 12% above the best results obtained for the pixel-based algorithms tested. The incorporation of context information to the object-based classification allowed better identification of fuel types with similar spectral behaviour.
Additional keywords: allocation disagreement, Maximum Likelihood, Neural Network, Object-Based Image Analysis, quantity disagreement, Support Vector Machine.
References
Andrews PL (2009) BehavePlus fire modeling system, version 5.0: variables. Department of Agriculture, Forest Service, Rocky Mountain Research Station, General Technical Report RMRS-GTR-213WWW-Revised. (Fort Collins, CO)Andrews PL, Queen LLP (2001) Fire modeling and information system technology. International Journal of Wildland Fire 10, 343–352.
| Fire modeling and information system technology.Crossref | GoogleScholarGoogle Scholar |
Arco Md, Wildpret W, Pérez de Paz PL, Rodríguez O, Acebes JR, García A, Martín VE, Reyes JA, Salas M, Díaz MA, Bermejo JA, González R, Cabrera MV, García S (2003) Cartografía 1 : 25 000 de la Vegetación Canaria. GRAFCAN S.A. (Santa Cruz de Tenerife, Spain)
Arroyo LA, Healey SP, Cohen WB, Cocero D, Manzanera JA (2006) Using object-oriented classification and high-resolution imagery to map fuel types in a Mediterranean region. Journal of Geophysical Research 111, G04S04
| Using object-oriented classification and high-resolution imagery to map fuel types in a Mediterranean region.Crossref | GoogleScholarGoogle Scholar |
Arroyo L, Pascual C, Manzanera J (2008) Fire models and methods to map fuel types: the role of remote sensing. Forest Ecology and Management 256, 1239–1252.
| Fire models and methods to map fuel types: the role of remote sensing.Crossref | GoogleScholarGoogle Scholar |
Bagan H, Wang Q, Watanabe M, Kameyama S, Bao Y (2008) Land-cover classification using ASTER multi-band combinations based on wavelet fusion and SOM Neural Network. Photogrammetric Engineering and Remote Sensing 74, 333–342.
Blaschke T (2010) Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing 65, 2–16.
| Object based image analysis for remote sensing.Crossref | GoogleScholarGoogle Scholar |
Burgan RE, Klaver RW, Klaver JM (1998) Fuel models and fire potential from satellite and surface observations. International Journal of Wildland Fire 8, 159–170.
| Fuel models and fire potential from satellite and surface observations.Crossref | GoogleScholarGoogle Scholar |
Coluzzi R, Didonna I, Lanorte A, Lasaponara R (2007) Mapping forest fuel types by using satellite ASTER data and neural nets. Proceedings of the Society for Photo-Instrumentation Engineers 6742, 67420T
| Mapping forest fuel types by using satellite ASTER data and neural nets.Crossref | GoogleScholarGoogle Scholar |
Falkowski M, Gessler P, Morgan P, Hudak A, Smith A (2005) Characterizing and mapping forest fire fuels using ASTER imagery and gradient modeling. Forest Ecology and Management 217, 129–146.
| Characterizing and mapping forest fire fuels using ASTER imagery and gradient modeling.Crossref | GoogleScholarGoogle Scholar |
Finney MA (2003) Calculation of fire spread rates across random landscapes. International Journal of Wildland Fire 12, 167–174.
| Calculation of fire spread rates across random landscapes.Crossref | GoogleScholarGoogle Scholar |
Finney MA (2004) FARSITE: Fire Area Simulator–model development and evaluation. USDA Forest Service, Rocky Mountain Research Station, Research Paper RMRS-RP-4. (Ogden, UT)
Finney MA (2006) An overview of FlamMap fire modeling capabilities. In ‘Fuels management – How to Measure Success: Conference Proceedings’, 28–30 March 2006, Portland, OR. (Eds PL Andrews, BW Butler) USDA Forest Service, Rocky Mountain Research Station, Proceedings RMRS-P-41. pp. 213–220. (Fort Collins, CO)
Hagner O, Reese H (2007) A method for calibrated maximum likelihood classification of forest types. Remote Sensing of Environment 110, 438–444.
| A method for calibrated maximum likelihood classification of forest types.Crossref | GoogleScholarGoogle Scholar |
Huang C, Townshend JRG (2002) An assessment of support vector machines for land cover classification. International Journal of Remote Sensing 23, 725–749.
| An assessment of support vector machines for land cover classification.Crossref | GoogleScholarGoogle Scholar |
Huete AR (1989) Soil influences in remotely sensed vegetation canopy spectra. In ‘Theory and Applications of Optical Remote Sensing’. (Ed. G Asrar) pp. 107–141. (Wiley: New York)
Jiang Z, Huete A, Didan K, Miura T (2008) Development of a two-band enhanced vegetation index without a blue band. Remote Sensing of Environment 112, 3833–3845.
| Development of a two-band enhanced vegetation index without a blue band.Crossref | GoogleScholarGoogle Scholar |
Keane RE, Garner JL, Schmidt KM, Long DG, Menakis JP, Finney MA (1998) Development of input data layers for the FARSITE fire growth model for the Selway–Bitterroot Wilderness Complex, USA. USDA Forest Service, Rocky Mountain Research Station, General Technical Report RMRS-GTR-3 (Ogden, UT)
Lasaponara R, Lanorte A (2007) Remotely sensed characterization of forest fuel types by using satellite ASTER data. International Journal of Applied Earth Observation and Geoinformation 9, 225–234.
| Remotely sensed characterization of forest fuel types by using satellite ASTER data.Crossref | GoogleScholarGoogle Scholar |
MAPA (1989) Clave fotográfica para la identificación de modelos de combustibles. ICONA, Ministerio de Agricultura, Pesca y Alimentación. (Madrid, Spain) [in Spanish]
Martínez Chamorro J (2011) Plan de Adaptación de Canarias al Cambio Climático. (Ed. G de Canarias), Agencia Canaria de Desarrollo Sostenible y Cambio Climático (Las Palmas de Gran Canaria, Spain) [in Spanish]
MdMA (2002) Mapa forestal de España a escala 1 : 50 000 de la provincia de Santa Cruz de Tenerife. Trabajos de campo realizados en el año 2.002 con soporte de ortofoto digital procedente de la Comunidad Autónoma de Canarias. Ministerio de Medio Ambiente, Organismo Autónomo de Parques Nacionales, Pesca y Alimentación, Soporte CD-Rom [in Spanish]
Mercier G, Lennon M (2003) Support vector machines for hyperspectral image classification with spectral-based kernels. In ‘Geoscience and Remote Sensing Symposium, 2003. IGARSS ‘03. Proceedings. 2003 IEEE International’, 21–25 July 2003, Toulouse, France. Vol. 1, pp. 288–290. (CNRS: Brest, France)
MMARM (2011) Los incendios forestales en España. Área de Defensa Contra Incendios, Ministerio del Medio Ambiente, Rural y Marino. (Madrid) [in Spanish]
Moreno JM, Rodríguez-Urbieta I, Zabala G, Martín M (2009) Cambio Climático y Riesgo de Incendios Forestales en Castilla-La Mancha. In ‘Impactos del Cambio Climático en Castilla-La Mancha. Primer Informe’. pp. 340–362. (Fundación General de Medio Ambiente, Junta de Comunidades de Castilla-La Mancha: Toledo) [in Spanish]
Mutlu M, Popescu SC, Zhao K (2008) Sensitivity analysis of fire behavior modeling with LiDAR-derived surface fuel maps. Forest Ecology and Management 256, 289–294.
| Sensitivity analysis of fire behavior modeling with LiDAR-derived surface fuel maps.Crossref | GoogleScholarGoogle Scholar |
Pontius RG, Millones M (2011) Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment. International Journal of Remote Sensing 32, 4407–4429.
| Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment.Crossref | GoogleScholarGoogle Scholar |
Pyne SJ, Andrews PL, Laven PD (1996) ‘Introduction to Wildland Fire’, 2nd edn. (Wiley: New York)
Qi J, Chehbouni A, Huete AR, Kerr YH, Sorooshian S (1994) A modified soil adjusted vegetation index. Remote Sensing of Environment 48, 119–126.
| A modified soil adjusted vegetation index.Crossref | GoogleScholarGoogle Scholar |
Riaño D, Chuvieco E, Salas J, Palacios-Orueta A, Bastarrika A (2002) Generation of fuel type maps from Landsat TM images and ancillary data in Mediterranean ecosystems. Canadian Journal of Forest Research 32, 1301–1315.
| Generation of fuel type maps from Landsat TM images and ancillary data in Mediterranean ecosystems.Crossref | GoogleScholarGoogle Scholar |
Rothermel RC (1972) A mathematical model for predicting fire spread in wildland fuels. USDA Intermountain Forest and Range Experiment Station, Research Paper INT-115 (Ogden, UT)
Rothermel RC (1983) How to predict the spread and intensity of forest and range fires. USDA Intermountain Forest and Range Experiment Station, Research Paper INT-143 (Ogden, UT)
Rothermel RC (1991) Predicting behavior and size of crown fires in the Northern Rocky Mountains. USDA Intermountain Forest and Range Experiment Station, Research Paper INT-438 (Ogden, UT)
Rouse JW, Haas RH, Schell JA, Deering DW (1973) Monitoring vegetation systems in the Great Plains with ERTS. In ‘Third Earth Resources Technology Satellite-1 Symposium – Volume I: Technical Presentations’, 10–14 December 1973, Washington, DC. (Eds SC Freden, EP Mercanti, MA Becker) NASA, Scientific and Technical Information Office, SP-351, pp. 309–317. (Washington, DC)
Rumelhart DE, Hinton DE, Williams RJ (1986) Learning internal representations by error propagation. In ‘Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. 1.’ (Eds DE Rumelhart, JL McClelland) pp. 318–364. (MIT Press: Cambridge, MA)
Scott JH, Burgan RE (2005) Standard fire behavior fuel models: a comprehensive set for use with Rothermel’s surface fire spread model. USDA Forest Service, Rocky Mountain Research Station, General Technical Report RMRS-GTR-153. (Fort Collins, CO)
Smith AMS (2007) How to convert ASTER radiance values to reflectance. (University of Idaho: Moscow, ID) Available at www.cnrhome.uidaho.edu/default.aspx?pid=85984 [Verified 28 August 2012]
Tanase MA, Gitas IZ (2008) An examination of the effects of spatial resolution and image analysis technique on indirect fuel mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 1, 220–229.
| An examination of the effects of spatial resolution and image analysis technique on indirect fuel mapping.Crossref | GoogleScholarGoogle Scholar |
Teillet PM, Guindon B, Goodenough DG (1982) On the slope-aspect correction of multispectral scanner data. Canadian Journal of Remote Sensing 8, 84–106.
Tymstra C, Bryce RW, Wotton BM, Taylor SW, Armitage OB (2010) Development and structure of Prometheus: the Canadian wildland fire growth simulation model. Natural Resources Cananda, Canadian Forest Service, Northern Forestry Centre, Information Report NOR-X-417. (Edmonton, AB)
Vapnik VN (2000) ‘The Nature of Statistical Learning’ 2nd edn. (Springer–Verlag Inc: New York)
VVAA (2002) Mapa 1 : 25 000 de usos del suelo. GRAFCAN S.A. (Santa Cruz de Tenerife, Spain) [in Spanish]
