Ordination and hyperspectral remote sensing approach to classify peatland biotopes along soil moisture and fertility gradients

Remote Sensing of Environment

Volumn 124, Issue , 2012, Pages 596-609

  Middleton, Maarit ^a   Närhi, Paavo ^a   Arkimaa, Hilkka ^a   Hyvönen, Eija ^a   Kuosmanen, Viljo ^a   Treitz, Paul ^b   Sutinen, Raimo ^a  

^a GEOLOGICAL SURVEY OF FINLAND   (Finland)

^b QUEEN S UNIVERSITY   (Canada)

Author keywords

Bog; Boreal peatland; Canonical correspondence analysis; Environmental variables; Eutrophic fen; Hyperspectral; Plant community; Sedge fen; Support vector machines; Swamp

Indexed keywords

BOG; BOREAL PEATLANDS; CANONICAL CORRESPONDENCE ANALYSIS; ENVIRONMENTAL VARIABLES; EUTROPHIC FEN; HYPERSPECTRAL; PLANT COMMUNITIES; SEDGE FEN; SWAMP;

ELECTRIC CONDUCTIVITY; EUTROPHICATION; METEOROLOGICAL PROBLEMS; PERMITTIVITY; PLANTS (BOTANY); REMOTE SENSING; SOIL MOISTURE; SUPPORT VECTOR MACHINES;

WETLANDS;

ACCURACY ASSESSMENT; BIOTOPE; BOREAL FOREST; CANONICAL ANALYSIS; CORRESPONDENCE ANALYSIS; DATA SET; ENVIRONMENTAL GRADIENT; FEN; FUZZY MATHEMATICS; IMAGE CLASSIFICATION; MAPPING; MONITORING; MOSS; ORDINATION; PEATLAND; PH; PLANT COMMUNITY; REMOTE SENSING; SOIL FERTILITY; SOIL MOISTURE; SPECIES DIVERSITY; SPECIES INVENTORY; SWAMP;

FINLAND;

CAREX LASIOCARPA; CAREX ROSTRATA; COMARUM PALUSTRE; ERIOPHORUM VAGINATUM; RUBUS; RUBUS CHAMAEMORUS; SPHAGNUM; SPHAGNUM ANGUSTIFOLIUM; SPHAGNUM FUSCUM; SPHAGNUM MAJUS; TRICHOPHORUM CESPITOSUM;

EID: 84863687740     PISSN: 00344257     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.rse.2012.06.010     Document Type: Article

References (99)

1. Aapala K. Soiden uhanalainen lajisto. Suomen ympäristö 2001, 490:149-182. K. Aapala (Ed.).
2. Andersen R., Poulin M., Borcard D., Laiho R., Laine J., Vasander H., et al. Environmental control and spatial structures in peatland vegetation. Journal of Vegetation Science 2011, 22:878-890.
3. Anderson M.J. A new method for non-parametric multivariate analysis of variance. Australian Journal of Ecology 2001, 26:32-46.
4. Arkimaa H., Laitinen J., Korhonen R., Moisanen M., Hirvasniemi T., Kuosmanen V. Spectral reflectance properties of Sphagnum moss species in Finnish mires. 6th EARseL imaging spectroscopy SIG workshop. Imaging spectroscopy: Innovative tool for scientific and commercial environmental applications 2009, URL: http://www.earsel.org/workshops/IS_Tel-Aviv_2009/PDF/earsel-PROCEEDINGS/3061%20Arkimaa.pdf.
5. Arkimaa H., Middleton M., Hyvönen E., Kuosmanen V., Laitinen J., Sutinen R. Mire site type mapping of boreal peatlands with hyperspectral airborne HyMap in northern Finland. 4th workshop on imaging spectroscopy. New quality in environmental studies 2005, 329-336. B. Zagajewski, M. Sobzak, M. Wrzesien (Eds.).
6. Asner G.P. Biophysical and biochemical sources of variability in canopy reflectance. Remote Sensing of Environment 1998, 64:234-253.
7. Atkinson D.M., Treitz P. Ecological classifications derived from spectral and vegetation data for Cape Bounty, Melville Island. IPY GeoNorth - International circumpolar conference on geospatial sciences and applications 2007, URL: http://geog.queensu.ca/larsees/pdfs/AtkinsonD_North2007_P.pdf.
8. Bedrock of Finland - DigiKP Digital map database [Electronic resource]. Espoo: Geological Survey of Finland [refered dd.mm.yyyy] 2009, Version 1.0. Available at: http://www.geo.fi/en/bedrock.html.
9. Boresjö Bronge L., Abenius J., Eriksson J., Kellner O. Satellite data for monitoring of Swedish wetlands. The first international symposium on GlobWetland: Looking at wetlands from space 2006, CD-ROM. H. Sawaya-Lacoste (Ed.).
10. Boresjö Bronge L., Näslund-Landenmark B. Wetland classification for Swedish CORINE land cover adopting a semi-automatic interactive approach. Canadian Journal of Remote Sensing 2002, 28:139-155.
11. Bragazza L., Gerdol R. Are nutrient availability and acidity-alkalinity gradients related in Sphagnum-dominated peatlands?. Journal of Vegetation Science 2002, 13:473-482.
12. Bray J.R., Curtis J.T. An ordination of the upland forest communities of southern Wisconsin. Ecological Monographs 1957, 27:325-349.
13. Bridgham S., Pastor J., Janssens J., Chapin C., Malterer T. Multiple limiting gradients in peatlands: A call for a new paradigm. Wetlands 1996, 16:45-65.
14. Bruzzone L., Melgani F. Classification of hyperspectral remote-sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing 2004, 42:1778-1790.
15. Buckingham R., Staenz K. Review of current and planned civilian space hyperspectral sensors for EO. Canadian Journal of Remote Sensing 2008, 34:187-197.
16. Burges C.J.C. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery 1998, 2:121-167.
17. Cajander A.K. The theory of forests types. Acta Forestalia Fennica 1926, 29:1-108.
18. Cocks T., Jenssen R., Stewart A., Wilson L., Shields T. The HyMapTM airborne hyperspectral sensor: The system, calibration and performance. 1st EARSEL workshop on imaging spectroscopy 1998, 1-7. M.E. Schaepman, D. Schläpfer, K. Itten (Eds.).
19. Dahl T.E., Watmough M.D. Current approaches to wetland status and trends monitoring in prairie Canada and the continental United States of America. Canadian Journal of Remote Sensing 2007, 33:S17-S27.
20. Dechka J.A., Franklin S.E., Watmough M.D., Bennett R.P., Ingstrup D.W. Classification of wetland habitat and vegetation communities using multi-temporal Ikonos imagery in southern Saskatchewan. Canadian Journal of Remote Sensing 2002, 28:679-685.
21. Drebs A., Helminen J., Karlsson P., Nordlund A., Rissanen P. Tilastoja Suomen ilmastosta 1971-2000 2002, 99. Ilmatieteen laitos, Helsinki.
22. Eurola S., Hicks S., Kaakinen E. Key to Finnish mire types. European mires 1984, 11-118. Academic Press, London. P.D. Moore (Ed.).
23. Eurola S., Huttunen A., Kukko-oja K. Suokasvillisuusopas 1995, 81. Oulanka Biological Station, University of Oulu, Oulu.
24. Feilhauer H., Faude U., Schmidtlein S. Combining Isomap ordination and imaging spectroscopy to map continuous floristic gradients in a heterogeneous landscape. Remote Sensing of Environment 2011, 115:2513-2524.
25. Foody G.M. Fuzzy modelling of vegetation from remotely sensed imagery. Ecological Modelling 1996, 85:3-12.
26. Foody G.M., Mathur A. The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM. Remote Sensing of Environment 2006, 103:179-189.
27. Fournier R.A., Grenier M., Lavoie A., Hélie R. Towards a strategy to implement the Canadian Wetland Inventory using satellite remote sensing. Canadian Journal of Remote Sensing 2007, 33:S1-S16.
28. Franklin J. Predictive vegetation mapping: Geographic modelling of biospatial patterns in relation to environmental gradients. Progress in Physical Geography 1995, 19:474-499.
29. Grenier M., Demers A., Labrecque S., Benoit M., Fournier R.A., Drolet B. An object-based method to map wetland using RADARSAT-1 and Landsat ETM images: Test case on two sites in Quebec, Canada. Canadian Journal of Remote Sensing 2007, 33:S28-S45.
30. Gunnarsson U., Malmer N., Rydin H. Dynamics or constancy in Sphagnum dominated mire ecosystems? A 40-year study. Ecography 2002, 25:685-704.
31. Haapanen R., Tokola T. Creating a digital treeless peatland map by using satellite image interpretation. Scandinavian Journal of Forest Research 2007, 22:48-59.
32. Harris A., Bryant R.G., Baird A.J. Mapping the effects of water stress on Sphagnum: Preliminary observations using airborne remote sensing. Remote Sensing of Environment 2006, 100:363-378.
33. Heino R., Hellsten E. Climatological statistics in Finland 1961-1980. Meteorological yearbook of Finland 1983, 494. The Finnish Meteorological Institute, Helsinki.
34. Hildén M., Auvinen A., Primmer E. Suomen biodiversiteettiohjelman arviointi 2005, 251. Suomen ympäristökeskus, Helsinki.
35. Hogg A.R., Todd K.W. Automated discrimination of upland and wetland using terrain derivatives. Canadian Journal of Remote Sensing 2007, 33:S68-S83.
36. Hökkä H., Kaunisto S., Korhonen K.T., Päivänen J., Reinikainen A., Tomppo E. Suomen suometsät 1951-94. Metsätieteen aikakauskirja 2B/2002 2002, 201-357. In Finnish.
37. Holopainen M., Jauhiainen S. Detection of peatland vegetation types using digitized aerial photographs. Canadian Journal of Remote Sensing 1999, 25:475-485.
38. Huang L.X., Sheng G. Classification of the Lakkasuo peatland ecosystem using remote sensing. Environmental Informatics Archives 2005, 3:295-305.
39. Jongman R.H.G., Ter Braak C.J.F., van Tongeren O.F.R. Data analysis in community and landscape ecology 1995, 324. Cambridge University Press, Cambridge.
40. Juvonen T., Ojanen M., Tanttu J.T., Rosnell J. Kaukokartoituksen ympäristösovellukset: suotyyppien erottaminen pintalämpötilojen perusteella. Suo 1997, 48:9-19. (In Finnish).
41. Kaakinen E., Aapala K., Kokko A. Diversity and current condition of Finnish mires. FINLAND - Fenland: Research and sustainable utilisation of mires and peat 2008, 34-53. Suoreura ry, Maahenki Oy, Finland. R. Korhonen, S. Sarkola, L. Korpela (Eds.).
42. Kaufman L., Rousseeuw P.J. Finding groups in data: An introduction to cluster analysis 2008, 368. John Wiley & Sons, New York.
43. Kohonen T. Self-organizing maps 2001, 501. Springer, Berlin.
44. Korpela I., Koskinen M., Vasander H., Holopainen M., Minkkinen K. Airborne small-footprint discrete-return LiDAR data in the assessment of boreal mire surface patterns, vegetation, and habitats. Forest Ecology and Management 2009, 258:1549-1566.
45. Laine J., Vasander H. Suotyypit ja niiden tunnistaminen 2005, 110. Metsäkustannus, Helsinki, In Finnish.
46. Laitinen J., Rehell S., Huttunen A., Tahvanainen T., Heikkilä R., Lindholm T. Mire systems in Finland - Special view to aapa mires and their water-flow pattern. Suo 2007, 58:1-26.
47. Landgrebe T.C.W., Duin R.P.W. Approximating the multiclass ROC by pairwise analysis. Pattern Recognition Letters 2007, 28:1747-1758.
48. Lang M., Kuusk A., Nilson T., Lükk T., Pehk M., Alm G. Reflectance spectra of ground vegetation in sub-boreal forests URL:, (accessed 22nd October, 2011). http://www.aai.ee/bgf/ger2600/.
49. Li J., Chen W., Touzi R. Optimum RADARSAT-1 configurations for wetlands discrimination: A case study of the Mer Bleue peat bog. Canadian Journal of Remote Sensing 2007, 33:S46-S55.
50. Maechler M., Rousseeuw P., Struyf A., Hubert M. Cluster analysis extended URL:, (accessed 20th March, 2011). http://cran.r-project.org/web/packages/cluster/index.html.
51. Malik R.N., Husain S.Z. Classification and ordination of vegetation communities of the Lohibehr reserve forest and its surrounding areas, Rawalpindin, Pakistan. Pakistanian Journal of Botany 2006, 38:543-558.
52. Malmer N. Vegetational gradients in relation to environmental conditions in northwestern European mires. Canadian Journal of Botany 1986, 64:375-383.
53. Manel S., Williams H.C., Ormerod S.J. Evaluating presence-absence models in ecology: The need to account for prevalence. Journal of Applied Ecology 2001, 38:921-931.
54. Mantero P., Moser G., Serpico S.B. Partially supervised classification of remote sensing images through SVM-based probability density estimation. IEEE Transactions on Geoscience and Remote Sensing 2005, 43:559-570.
55. McMorrow J., Cutler M., Al-Roichi A., Evans M. Hyperspectral remote sensing of peat humification. Imaging Spectroscopy: New Quality in Environmental Studies 2005, 193-204.
56. Middleton M., Arkimaa H., Hyvönen E., Närhi P., Kuosmanen V., Sutinen R. Classification of boreal mire biotypes with hyperspectral airborne HyMap in Finland. 6th EARseL imaging spectroscopy SIG workshop. Imaging spectroscopy: Innovative tool for scientific and commercial environmental applications 2009, URL: http://www.earsel.org/workshops/IS_Tel-Aviv_2009/PDF/earsel-PROCEEDINGS/3045%20Middleton.pdf.
57. Montanarella L., Jones R.J.A., Hiederer R. The distribution of peatland in Europe. Mires and Peat 2006, 1:1-10.
58. Moore T.R., Knowles R. The influence of water table levels on methane and carbon dioxide emissions from peatland soils. Canadian Journal of Soil Science 1989, 69:77-81.
59. Mountrakis G., Im J., Ogole C. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing 2011, 66:247-259.
60. Närhi P., Middleton M., Hyvönen E., Piekkari M., Sutinen R. Central boreal mire plant communities along soil nutrient potential and water content gradients. Plant and Soil 2010, 331:257-264.
61. Ohmann J.L., Gregory M.J. Predictive mapping of forest composition and structure with direct gradient analysis and nearest-neighbor imputation in coastal Oregon, U.S.A. Canadian Journal of Forest Research 2002, 32:725-741.
62. Økland R.H., Økland T., Rydgren K. A Scandinavian perspective on ecological gradients in north-west European mires: Reply to Wheeler and Proctor. Journal of Ecology 2001, 89:481-486.
63. Oksanen J., Blanchet F.G., Kindt R., Legendre P., Minchin P.R., O'Hara R.B., et al. vegan: Community ecology package URL:, (accessed 07 February, 2011). http://vegan.r-forge.r-project.org/.
64. Pal M., Foody G.M. Feature selection for classification of hyperspectral data by SVM. IEEE Transactions on Geoscience and Remote Sensing 2010, 48:2297-2307.
65. Park S.H., Goo J.M., Jo C. Receiver operating characteristic (ROC) curve: Practical review for radiologists. Korean Journal of Radiology 2004, 5:11-18.
66. Puranen, R., Sulkanen, K., Nissinen, R., & Simelius, P. (1999). Ominaisvastusluotaimet ja vastustalikot (Resistivity probes and forks). Unpublished report Q15/27.4/99/2.8. Espoo: Geological Survey of Finland. URL: In Finnish. http://arkisto.gsf.fi/q15/Q15_27.4_99_2.pdf.
67. Rabe A., van der Linden S., Hostert P. imageSVM, Version 2.1 URL:. http://www.hu-geomatics.de.
68. Rhoades J.D., Oster J.D. Solute content. Methods of soil analysis part 1: Physical and mineralogical methods 1986, 985-1006. American Society of Agronomy, Madison. A. Klute (Ed.).
69. Richter R. Atmospheric/topographic correction for airborne imagery, ATCOR-4 user guide, version 3 URL:. http://atcor.info/pdf/atcor4_manual.pdf.
70. Roth C.H., Malicki M.A., Plagge R. Empirical evaluation of the relationship between soil dielectric constant and volumetric water content as the basis for calibrating soil moisture measurements by TDR. Journal of Soil Science 1992, 43:1-13.
71. Sánchez-Azofeifa A., Rivard B., Wright J., Feng J.-L., Li P., Chong M.M., et al. Estimation of the distribution of Tabebuia guayacan (Bignoniaceae) using high-resolution remote sensing imagery. Sensors 2011, 11:3831-3851.
72. Schläpfer D. PARametric GEocoding, user guide, version 1.3.4 2001.
73. Schmidtlein S., Sassin J. Mapping of continuous floristic gradients in grasslands using hyperspectral imagery. Remote Sensing of Environment 2004, 92:126-138.
74. Schmidtlein S., Zimmermann P., Schüpferling R., Weiß C. Mapping the floristic continuum: Ordination space position estimated from imaging spectroscopy. Journal of Vegetation Science 2007, 18:131-140.
75. 2 fluxes from peat in boreal mires under varying temperature and moisture conditions. Journal of Ecology 1996, 84:219-228.
76. Sing T., Sander O., Beerenwinkel N., Lengaue T. ROCR: Visualizing classifier performance in R. Bioinformatics 2005, 21:3940-3941.
77. Sjörs H., Gunnarsson U. Calcium and pH in north and central Swedish mire waters. Journal of Ecology 2002, 90:650-657.
78. Tahvanainen T., Sallantaus T., Heikkilä R., Tolonen K. Spatial variation of mire surface water chemisrty and vegetation in northeastern Finland. Annales Botanici Fennici 2002, 39:235-251.
79. Ter Braak C.J.F. Canonical correspondence analysis: A new eigenvector technique for multivariate direct gradient analysis. Ecology 1986, 67:1167-1179.
80. Ter Braak C.J.F. The analysis of vegetation-environment relationships by canonical correspondence analysis. Vegetatio 1987, 64:69-77.
81. Thessler S., Ruokolainen K., Tuomisto H., Tomppo E. Mapping gradual landscape-scale floristic changes in Amazonian primary rain forests by combining ordination and remote sensing. Global Ecology and Biogeography 2005, 14:315-325.
82. Thomas V., Treitz P., Jelinski D., Miller J., Lafleur P., McCaughey J.H. Image classification of a northern peatland complex using spectral and plant community data. Remote Sensing of Environment 2003, 84:83-99.
83. Topographic database 1:20000. Digital map database. Helsinki: National Land Survey of Finland. (accessed 14th May, 2005).
84. Törmä M., Härmä P., Hatunen S., Teiniranta R., Kallio M., Järvenpää E. Change detection for Finnish CORINE land cover classification. SPIE Proceedings 2011, 8181:81810Q. U. Michel, D.L. Civco (Eds.).
85. Touzi R., Deschamps A., Rother G. Wetland characterization using polarimetric RADARSAT-2 capability. Canadian Journal of Remote Sensing 2007, 33:S56-S67.
86. Töyrä J., Pietroniro A. Towards operational monitoring of a northern wetland using geomatics-based techniques. Remote Sensing of Environment 2005, 97:174-191.
87. Trodd N.M. Analysis and representation of heathland vegetation from near-ground level remotely-sensed data. Global Ecology and Biogeography Letters 1996, 5:206-216.
88. Tuominen S., Aapala K. Hyvinkään Petkelsuon muutokset 1936-1997 - esimerkki eri-aikaisten ilmakuvien käytöstä keidassoiden muutosten seurannassa. Suomen Ympäristö 2001, 490:45-86. (In Finnish).
89. Turunen J. Development of Finnish peatland area and carbon storage 1950-2000. Boreal Environment Research 2008, 13:319-334.
90. Uhanalaisten lajien II seurantaryhmä Suomen lajien uhanalaisuus 2000 2001, 432. The Ministry of Environment, Edita, Helsinki, In Finnish.
91. Van de Ven C.M., Weiss S.B. Mapping arid vegetation species distributions in the White Mountains, eastern California, using AVIRIS, topography, and geology. AVIRIS airborne geoscience workshop proceedings 2001, URL: ftp://popo.jpl.nasa.gov/pub/docs/workshops/aviris.proceedings.html.
92. Van der Laana M., Pollardb K., Bryanc J. A new partitioning around medoids algorithm. Journal of Statistical Computation and Simulation 2003, 73:575-584.
93. Van der Linden S., Janz A., Waske B., Eiden M., Hostert P. Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines. Journal of Applied Remote Sensing 2007, 1:013543.
94. Van der Linden S., Rabe A., Wirth F., Suess S., Okujeni A., Hostert P. imageSVM classification, manual for application: imageSVM (2.1) 2010.
95. Van Gaalen K.E., Flanagan L.B., Peddle D.R. Photosynthesis, chlorophyll fluorescence and spectral reflectance in Sphagnum moss at varying water contents. Oecologia 2007, 153:19-28.
96. Virtanen K., Hänninen P., Kallinen R.-L., Vartiainen S., Herranen T., Jokisaari R. Suomen turvevarat 2000. Summary: The peat reserves of Finland in 2000 2003, 101. Geological Survey of Finland, Helsinki.
97. Wells E.D. Classification of peatland vegetation in Atlantic Canada. Vegetation Science 1996, 7:847-878.
98. Yu Z., Beilman D.W., Frolking S., MacDonald G.M., Roulet N.T., Camill P., et al. Peatlands and their role in the global carbon cycle. Remote Sensing of Environment 2011, 92:97-108.
99. Zimmermann N.E., Moisen G.G., Edwards T.C.J., Frescino T.S., Blackard J.A. Remote sensing-based predictors improve distribution models of rare, early successional and broadleaf tree species in Utah. Journal of Applied Ecology 2007, 44:1057-1067.