Mapping the biomass of Bornean tropical rain forest from remotely sensed data

Giles M. Foody, Mark E. Cutler, Julia McMorrow, Dieter Pelz, Hamzah Tangki, Doreen S. Boyd, Ian Douglas

    Research output: Contribution to journalArticle

    172 Citations (Scopus)

    Abstract

    The biomass and biomass dynamics of forests are major uncertainties in our understanding of tropical environments. Remote sensing is often the only practical means of acquiring information on forest biomass but has not always been used successfully. Here the conventional approaches to the estimation of forest biomass from remotely sensed data were evaluated relative to techniques based on the application of artificial neural networks. Together these approaches were used to estimate and map the biomass of tropical forests in north-eastern Borneo from Landsat TM data. The neural networks were found to be particularly suited to the application. A basic multilayer perceptron network, for example, provided estimates of biomass that were strongly correlated with those measured in the field (r= 0.80). Moreover, these estimates were more strongly correlated with biomass than those derived from 230 conventional vegetation indices, including the widely used normalized difference vegetation index (NDVI).
    Original languageEnglish
    Pages (from-to)379-387
    JournalGlobal Ecology and Biogeography
    Volume10
    Issue number4
    DOIs
    Publication statusPublished - Jul 2001

    Fingerprint

    tropical rain forests
    biomass
    neural networks
    tropical environment
    Landsat
    Borneo
    vegetation index
    tropical rain forest
    Landsat thematic mapper
    NDVI
    artificial neural network
    tropical forests
    tropical forest
    remote sensing
    uncertainty

    Keywords

    • Borneo
    • Land cover change
    • Landsat TM
    • NDVI
    • Neural network
    • Remote sensing
    • Tropical forest biomass

    Cite this

    Foody, Giles M. ; Cutler, Mark E. ; McMorrow, Julia ; Pelz, Dieter ; Tangki, Hamzah ; Boyd, Doreen S. ; Douglas, Ian. / Mapping the biomass of Bornean tropical rain forest from remotely sensed data. In: Global Ecology and Biogeography. 2001 ; Vol. 10, No. 4. pp. 379-387.
    @article{c2ae8b179ebf47b7b118f5163f526949,
    title = "Mapping the biomass of Bornean tropical rain forest from remotely sensed data",
    abstract = "The biomass and biomass dynamics of forests are major uncertainties in our understanding of tropical environments. Remote sensing is often the only practical means of acquiring information on forest biomass but has not always been used successfully. Here the conventional approaches to the estimation of forest biomass from remotely sensed data were evaluated relative to techniques based on the application of artificial neural networks. Together these approaches were used to estimate and map the biomass of tropical forests in north-eastern Borneo from Landsat TM data. The neural networks were found to be particularly suited to the application. A basic multilayer perceptron network, for example, provided estimates of biomass that were strongly correlated with those measured in the field (r= 0.80). Moreover, these estimates were more strongly correlated with biomass than those derived from 230 conventional vegetation indices, including the widely used normalized difference vegetation index (NDVI).",
    keywords = "Borneo, Land cover change, Landsat TM, NDVI, Neural network, Remote sensing, Tropical forest biomass",
    author = "Foody, {Giles M.} and Cutler, {Mark E.} and Julia McMorrow and Dieter Pelz and Hamzah Tangki and Boyd, {Doreen S.} and Ian Douglas",
    year = "2001",
    month = "7",
    doi = "10.1046/j.1466-822X.2001.00248.x",
    language = "English",
    volume = "10",
    pages = "379--387",
    journal = "Global Ecology and Biogeography",
    issn = "1466-822X",
    publisher = "Wiley",
    number = "4",

    }

    Mapping the biomass of Bornean tropical rain forest from remotely sensed data. / Foody, Giles M.; Cutler, Mark E.; McMorrow, Julia; Pelz, Dieter; Tangki, Hamzah; Boyd, Doreen S.; Douglas, Ian.

    In: Global Ecology and Biogeography, Vol. 10, No. 4, 07.2001, p. 379-387.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Mapping the biomass of Bornean tropical rain forest from remotely sensed data

    AU - Foody, Giles M.

    AU - Cutler, Mark E.

    AU - McMorrow, Julia

    AU - Pelz, Dieter

    AU - Tangki, Hamzah

    AU - Boyd, Doreen S.

    AU - Douglas, Ian

    PY - 2001/7

    Y1 - 2001/7

    N2 - The biomass and biomass dynamics of forests are major uncertainties in our understanding of tropical environments. Remote sensing is often the only practical means of acquiring information on forest biomass but has not always been used successfully. Here the conventional approaches to the estimation of forest biomass from remotely sensed data were evaluated relative to techniques based on the application of artificial neural networks. Together these approaches were used to estimate and map the biomass of tropical forests in north-eastern Borneo from Landsat TM data. The neural networks were found to be particularly suited to the application. A basic multilayer perceptron network, for example, provided estimates of biomass that were strongly correlated with those measured in the field (r= 0.80). Moreover, these estimates were more strongly correlated with biomass than those derived from 230 conventional vegetation indices, including the widely used normalized difference vegetation index (NDVI).

    AB - The biomass and biomass dynamics of forests are major uncertainties in our understanding of tropical environments. Remote sensing is often the only practical means of acquiring information on forest biomass but has not always been used successfully. Here the conventional approaches to the estimation of forest biomass from remotely sensed data were evaluated relative to techniques based on the application of artificial neural networks. Together these approaches were used to estimate and map the biomass of tropical forests in north-eastern Borneo from Landsat TM data. The neural networks were found to be particularly suited to the application. A basic multilayer perceptron network, for example, provided estimates of biomass that were strongly correlated with those measured in the field (r= 0.80). Moreover, these estimates were more strongly correlated with biomass than those derived from 230 conventional vegetation indices, including the widely used normalized difference vegetation index (NDVI).

    KW - Borneo

    KW - Land cover change

    KW - Landsat TM

    KW - NDVI

    KW - Neural network

    KW - Remote sensing

    KW - Tropical forest biomass

    U2 - 10.1046/j.1466-822X.2001.00248.x

    DO - 10.1046/j.1466-822X.2001.00248.x

    M3 - Article

    VL - 10

    SP - 379

    EP - 387

    JO - Global Ecology and Biogeography

    JF - Global Ecology and Biogeography

    SN - 1466-822X

    IS - 4

    ER -