Abstract
Mediterranean forests are characterized by spatiotemporal heterogeneity that is associated with Mediterranean climate, floristic biodiversity and topographic variability. Satellite remote sensing can be an effective tool for characterizing and monitoring forest vegetation distribution within these fragmented Mediterranean landscapes. The heterogeneity of Mediterranean vegetation, however, often exceeds the resolution typical of most satellite sensors. Hyper-spectral remote sensing technology demonstrates the capacity for accurate vegetation identification. The objective of this research is to determine to what extent forest types can be discriminated using different image analysis techniques and spectral band combinations of Hyperion satellite imagery. This research mapped forest types using a pixel-based Spectral Angle Mapper (SAM), nearest neighbour and membership function classifiers of the object-oriented classification. Hyperion classification was done after reducing Hyperion data using nine selected band combinations. Results indicate that the selection of band combination while reducing the Hyperion dataset improves classification results for both the overall and the individual forest type accuracy, in particular for the selected optimum Hyperion band combination. One shortcoming is that the performance of the best selected band combination was superior in terms of both overall and individual forest type accuracy when applying the membership classifier of the object-oriented method compared to SAM and nearest neighbour classifiers. However, all techniques seemed to suffer from a number of problems, such as spectral similarity among forest types, overall low energy response of the Hyperion sensor, Hyperion medium spatial resolution and spatiotemporal and spectral heterogeneity of the Mediterranean ecosystem at multiple scales.
Similar content being viewed by others
References
Alados CL, Pueyo Y, Barrantes O, Escos J, Giner L, Robles AB (2004) Variations in landscape patterns and vegetation cover between 1957 and 1994 in a semiarid Mediterranean ecosystem. Landsc Ecol 19(5):543–559
Ashoori H, Fahimnejad H, Alimohammadi A, Soofbaf SR (2008) Evaluation of the usefulness of texture measures for crop type classification by Hyperion data. Int Arch Photogram Rem Sens Spatial Inform Sci 8(37):999–1005
Bajwa SG, Bajcsy P, Groves P, Tian LF (2004) Hyperspectral image data mining for band selection in agricultural applications. Trans ASAE (Am Soc Agric Eng) 47(3):895–907
Blackburn GA, Steele CM (1999) Towards the remote sensing of matorral vegetation physiology: relationships between spectral reflectance, pigment, and biophysical characteristics of semiarid bushland canopies. Remote Sens Environ 70:278–292
Boucher Y, Poutier L, Achard V, Lenot X, Miesch C (2002) Validation and robustness of an atmospheric correction algorithm for hyper-spectral image. In: Algorithms and technologies for multispectral, hyper-spectral and ultraspectral imagery VIII, no. 4725–54. SPIE Aerosense, Orlando, pp 459–470
Boyd DS, Danson FM (2005) Satellite remote sensing of forest resources: three decades of research development. Prog Phys Geogr 29(1):1–26
Carleer A, Wolff E (2004) Exploitation of very high resolution satellite data for tree species identification. Photogramm Eng Rem S 70(1):135–140
Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37:35–46
Congalton RG, Green K (1999) Assessing the accuracy of remotely sensed data: principles and practices. Lewis Publications, Boca Raton
Datt B, McVicar TR, Van Niel TG, Jupp DLB, Pearlman JS (2003) Preprocessing EO-1 hyperion hyper-spectral data to support the application of agricultural indexes. IEEE T Geosci Remote 41(6):1246–1259
De Backer S, Kempeneers P, Debruyn W, Scheunders P (2004) Classification of Dune vegetation from remotely sensed hyper-spectral images image analysis and recognition. Springer, Heidelberg
Definiens Imagine (2004) eCognition, object-oriented image analysis, User Guide 4. Definiens Imagine GmbH, München
DigitalGlobe Inc (2005) QuickBird imagery products – product guide. DigitalGlobe, Inc. 1601 Dry Creek Drive, Ste 260, Longmont, Colorado 80503
Eckert Sm Kneubuhler M (2004) Application of Hyperion data to agricultural land classification and vegetation properties estimation in Switzerland. In: XXth ISPRS Congress, Istanbul, Turkey, 12–23 July 2004
Elatawneh A, Manakos I, Kalaitzidis C, Shneider T (2009) Land cover classification and unmixing of hyperion image in area of Anopoli. In: 29th Annual EARSeL Symposium Proceedings, Crete, Greece, 15–18 June 2009
ENVI (2008) User’s guide, version 4.5. ITT Industries Inc, Boulder
ERDAS (1999) Imagine Field Guide, 5th edition revised and expanded. ERDAS®, Inc, Atlanta
Foster JR, Townsend PA (2004) Linking hyperspectral imagery and forest inventories for forest assessment in the central Appalachians. Proceedings of the 14th Central Hardwood Forest Conference, Wooster, Ohio, 16–19 March 2004
Fridgen JJ, Hellmich R, Copenhaver K, Glaser JA (2006) Use of hyperspectral imagery to distinguish corn phenology. MAPPS/ASPRS 2006 Fall Conference, San Antonio, Texas, 6–10 November 2006
Gao Y, Mas JF (2008) A comparison of the performance of pixel-based and object based classification over images with various spatial resolutions. J Earth SCI 2(1):27–35
Geng XR, Zhao YC (2007) Principle of small target detection for hyper spectral imagery. Sci China Series D: Earth Sci 50(8):1225–1231
Gondard H, Romane F, Santa Regina I, Leonardi S (2006) Forest management and plant species diversity in chestnut stands of three Mediterranean areas. Biodivers Conserv 15(4):1129–1142
Gong P, Pu R, Biging GS, Larrieu MR (2003) Estimation of forest leaf area index using vegetation indices derived from Hyperion hyper-spectral data. IEEE T Geosci Remote 41:1355–1362
Goodenough DG, Dyk A, Niemann KO, Pearlman JS, Chen H, Han T, Murdoch M, West C (2003) Processing HYPERION and ALI for forest classification. IEEE T Geosci Remote 41(6):1321–1331
Govender M, Chetty K, Naiken V, Bulcock H (2008) A comparison of satellite hyper-spectral and multispectral remote sensing imagery for improved classification and mapping of vegetation. Water SA 34(2)
Hernandez-Stefanoni JL (2005) Relationships between landscape patterns and species richness of trees, shrubs and vines in a tropical forest. Plant Ecol 179(1):53–65
Jobin B, Laberesque S, Grenier M, Falardeau G (2008) Object based classification as an alternative approach to the traditional pixel-based classification to identify potential habitat of the grasshopper sparrow. Environ Manage 41(1):20–31
Kaarna A, Toivanen P, Keranen P (2006) Compression and classification methods for hyper-spectral images. Pattern Recognit Image Anal 16(3):413–424
Keramitsoglou I, Kontoes C, Sykioti O, Sifakis N, Xofis P (2008) Reliable, accurate and timely forest mapping for wildfire management using ASTER and Hyperion satellite imagery. Forest Ecol Manag 255:3556–3562
Kiefer RW, Lillesand T (1999) Remote sensing and image interpretation. Wiley, London
Krahwinkler P, Rossmann J (2010) Tree species classification based on the analysis of hyperspectral remote sensing data. 30th EARSeL symposium: remote sensing for science, education and culture, Paris, France, 31 May to 3 June 2010
Kuenzer C, Bluemel A, Gebhardt S, Quoc TV, Dech S (2011) Remote sensing of mangrove ecosystems: a review. Remote Sens 3:878–928
Lawrence RL, Wood SD, Sheley RL (2006) Mapping invasive plants using hyper-spectral imagery and Breiman Cutler classifications (randomForest). Remote Sens Environ 100(3):356–362
Legleiter CJ (2003) Spectrally driven classification of high spatial resolution hyper-spectral imagery; a tool for mapping in stream habitat. Environ Manage 32(3):399–411
Liew SC, Chang CW, Lim KH (2002) Hyper-spectral land cover classification of EO-1 Hyperion data by principal component analysis and pixel unmixing. IEEE T Geosci Remote 6:3111–3113
Mahbooba J, Khattak U, Rahman M (2011). Forest tree species classification using multispectral satellite imageries. First International Geomatics Symposium, Jeddah, Saudi Arabia, 10–13 May 2011
Mallinis G, Koutsias N, Tsakiri-Strati M, Karteris M (2008) Object based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site. Photogramm Eng Rem S 63(2):237–250
Mathur A, Bruce LM, Robles W, Madsen J (2006). Identification of pertinent regions in spectro-temporal maps for vegetative target detection. ASPRS 2006 Annual Conference Reno, Nevada, 1–5 May 2006
Matinfar HR, Sarmadian F, Alavi Panah SK, Heck RJ (2007) Comparisons of OO and pixel-based classification of landuse/land cover types based on Landsat 7. ETM+ spectral bands (case study: arid region of Iran). Am Eurasian J Agric Environ Sci 2(4):448–456
Tanase MA, Gitas IZ (2008) An examination of the effects of spatial resolution and image analysis technique on indirect fuel mapping. Sel Top Appl Earth Obs Remote Sens 1(4):220–229
Nielsen AA (2001) Spectral mixture analysis; linear and semi parametric full and iterated partial unmixing in multi and hyper-spectral image data. J Math Imaging Vis 15(1–2):17–37
Ntouros KD, Gitas IZ, Silleos GN (2009) Mapping agricultural crops with EO-1 Hyperion data. First workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2009. WHISPERS ′09, in Grenoble, France, 26–28 August 2009
PCI Geomatics Enterprises Inc (2004) User’s Guide version 9.1. OrthoEngine, Geomatica
Quackenbush LJ, Ke Y, Kroll CN (2006) Investigating new advances in forest species classification: establishing a baseline. ASPRS 2006 Annual Conference, Reno, Nevada, 1–5 May 2006
Ray TW (1994) A FAQ on vegetation in remote sensing. http://www.yale.edu/ceo/Documentation/rsvegfaq.html Accessed 20 Oct 2010
Robila S (2005) An investigation of spectral metrics in hyper-spectral image pre-processing for classification. In: Geospatial goes global: from your neighborhood to the whole planet. ASPRS Annual Conference, Baltimore, Maryland, 7–11 March 2005
Rud R, Shoshany M, Alchanatis V, Cohern Y (2006) Application of spectral features ratios for improving classification in partially calibrated hyper-spectral imagery; a case study of separating Mediterranean vegetation species. J Real-Time Image Proc 1(2):143–152
Shataee S, Kellenberger T, Darvishsefat AA (2004). Forest types classification using ETM+ data in the north of IRAN: comparison of object-oriented with pixel-based classification technique. XXth ISPRS Congress, Istanbul, Turkey, 12–23 July 2004
Thenkabail PS, Enclona EA, Ashton MS, Van Der Meer B (2004) Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications. Remote Sens Environ 91:354–376
Torras O, Gil-Tena A, Saura S (2008) How does forest landscape structure explain tree species richness in a Mediterranean context. Biodivers Conserv 17(5):1227–1240
Vanhala P, Tamminen P, Fritze H (2005) Relationship between basal soil respiration rate, tree stand and soil characteristics in boreal forests. Environ Monit Assess 101(1–3):85–92
Waser LT, Baltsavias E, Ginzler C, Küchler M (2010) Semiautomatic classification of tree species by means of multitemporal airborne digital sensor data. ADS40 ISPRS TC VII Symposium—100 Years ISPRS, vol. XXXVIII, Part 7B, Vienna, Austria, 5–7 July 2010
Yuan J, Niu Z (2007) Classification using EO–1 Hyperion hyper spectral and ETM data. In: 4th International Conference of Fuzzy Systems and Knowledge Discovery, FSKD, 24–27 August 2007, Haikou, Hainan, China, (3): 538–542
Zeng Y, Schaepman ME, Bingfang WUB, Clevers JGPW, Bregt AK (2007) Using linear spectral unmixing of high spatial resolution and hyper-spectral data for geometric–optical modeling. In: Proceedings of the 10th International Symposium on Physical Measurements and Spectral Signatures in Remote Sensing (ISPMSRS'07), Davos, Switzerland, 12–14 March 2007
Zheng W, Zou C, Zhao L (2005) Generalized locally nearest-neighbor classifiers for object classification. Fuzzy systems and knowledge discovery. Lect Notes Comput Sc 3614(487):95–99
Zhou W, Troy A, Grove M (2008) Object based land cover classification and change analysis in the Baltimore Metropolitan Area using multi temporal high resolution remote sensed data. Sensors 8:1613–1636
Acknowledgments
The authors would like to thank several anonymous reviewers for their suggestions which helped improve this manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Etteieb, S., Louhaichi, M., Kalaitzidis, C. et al. Mediterranean forest mapping using hyper-spectral satellite imagery. Arab J Geosci 6, 5017–5032 (2013). https://doi.org/10.1007/s12517-012-0748-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12517-012-0748-6