Using artificial neural networks to map the spatial distribution of understorey bamboo from remote sensing data

Understorey vegetation is a critical component of biodiversity and an essential habitat component for many wildlife species. However, compared to overstorey, information about understorey vegetation distribution is scant, available mainly over small areas or through imprecise large area maps from tedious and time-consuming field surveys. A practical approach to classifying understorey vegetation from remote sensing data is needed for more accurate habitat analyses and biodiversity estimates. As a case study, we mapped the spatial distribution of understorey bamboo in Wolong Nature Reserve (south-western China) using remote sensing data from a leaf-on or growing season. Training on a limited set of ground data and using widely available Landsat TM data as input, a nonlinear artificial neural network achieved a classification accuracy of 80% despite the presence of co-occurring mid-storey and understorey vegetation. These results suggest that the influences of understorey vegetation on remote sensing data are available to practical approaches to classifying understorey vegetation. The success here to map bamboo distribution has important implications for giant panda conservation and provides a good foundation for developing methods to map the spatial distributions of other understorey plant species. Representative schematic of an artificial neural network. The arrows represent a feed-forward process of transforming input data, such as remote sensing imagery, to an output space (e.g. bamboo existence/absence). Networks are trained through a priori knowledge of output and input relations (ground data and corresponding remote sensing pixel values) and a reiterative back-propagation of training errors to update the hidden layer weights.

[1]  E. Odum Fundamentals of ecology , 1972 .

[2]  W. Bausch Soil background effects on reflectance-based crop coefficients for corn☆ , 1993 .

[3]  D. Roberts,et al.  Green vegetation, nonphotosynthetic vegetation, and soils in AVIRIS data , 1993 .

[4]  W. Bond,et al.  Mast Flowering and Semelparity in Bamboos: The Bamboo Fire Cycle Hypothesis , 1999, The American Naturalist.

[5]  Craig S. T. Daughtry,et al.  Sun angle, view angle, and background effects on spectral response of simulated balsam fir canopies , 1986 .

[6]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[7]  William W. Taylor,et al.  A Framework for Evaluating the Effects of Human Factors on Wildlife Habitat: the Case of Giant Pandas , 1999 .

[8]  G. Guyot,et al.  Factors affecting the spectral response of forest canopies: A review , 1989 .

[9]  Wang Wei,et al.  Giant Panda Ailuropoda melanoleuca behaviour and carrying capacity following a bamboo die-off , 1989 .

[10]  Yann Kerr,et al.  Leaf area index estimates using remotely sensed data and BRDF models in a semiarid region. , 2000 .

[11]  J. Settle,et al.  Subpixel measurement of tropical forest cover using AVHRR data , 1991 .

[12]  Stanley A. Morain,et al.  Surveying China's agricultural resources: Patterns and progress from space , 1986 .

[13]  R. Treuhaft,et al.  Vertical structure of vegetated land surfaces from interferometric and polarimetric radar , 2000 .

[14]  J. Liu,et al.  Ecological Degradation in Protected Areas: The Case of Wolong Nature Reserve for Giant Pandas , 2001, Science.

[15]  Ronald J. Hall,et al.  Variability of Landsat Thematic Mapper data in boreal deciduous and mixed wood stands with conifer understory , 1995 .

[16]  D. Lobell,et al.  A Biogeophysical Approach for Automated SWIR Unmixing of Soils and Vegetation , 2000 .

[17]  Hu Jinchu,et al.  The Giant Pandas of Wolong , 1985 .

[18]  S. Running,et al.  What does Remote Sensing Do for Ecology , 1991 .

[19]  M. C. Porwal,et al.  Attempted Understorey Characterization Using Aerial Photography in Kanha National Park, Madhya Pradesh, India , 1991, Environmental Conservation.

[20]  S. Running,et al.  Forest ecosystem processes at the watershed scale: Sensitivity to remotely-sensed leaf area index estimates , 1993 .

[21]  Gail A. Carpenter,et al.  A Neural Network Method for Mixture Estimation for Vegetation Mapping , 1999 .

[22]  G. Schaller,et al.  Responses of giant pandas to a bamboo die-off , 1988 .

[23]  Richard H. Waring,et al.  Remote Sensing of Leaf Area Index and Radiation Intercepted by Understory Vegetation , 1994 .

[24]  R. Jackson,et al.  Spectral response of a plant canopy with different soil backgrounds , 1985 .

[25]  S. Herrero The Giant Pandas of Wolong, George B. Schaller, Hu Jinchu, Pan Wenshi, Zhu Jing. University of Chicago Press, Chicago (1985), xix, +298. Price $25.00 , 1986 .

[26]  G. M. Foody,et al.  Relating the land-cover composition of mixed pixels to artificial neural network classification outpout , 1996 .

[27]  Giles M. Foody,et al.  An evaluation of some factors affecting the accuracy of classification by an artificial neural network , 1997 .

[28]  Steven W. Running,et al.  Remote sensing of temperate coniferous forest leaf area index The influence of canopy closure, understory vegetation and background reflectance , 1990 .

[29]  Adrian Luckman,et al.  A study of the relationship between radar backscatter and regenerating tropical forest biomass for spaceborne SAR instruments , 1997 .

[30]  F. J. García-Haro,et al.  A Mixture Modeling Approach to Estimate Vegetation Parameters for Heterogeneous Canopies in Remote Sensing , 2000 .

[31]  Jianguo Liu,et al.  Changes in Human Population Structure: Implications for Biodiversity Conservation , 1999 .

[32]  W. Cohen,et al.  Lidar Remote Sensing of the Canopy Structure and Biophysical Properties of Douglas-Fir Western Hemlock Forests , 1999 .

[33]  S. Gerstl,et al.  Nonlinear spectral mixing models for vegetative and soil surfaces , 1994 .

[34]  Robert M. Zink,et al.  Bird species diversity , 1996, Nature.

[35]  Robert De Wulf,et al.  Remote sensing for wildlife management: Giant panda habitat mapping from LANDSAT MSS images , 1988 .

[36]  P. Gong,et al.  Remote Sensing of Seasonal Leaf Area Index Across the Oregon Transect , 1994 .

[37]  John B. Adams,et al.  Classification of multispectral images based on fractions of endmembers: Application to land-cover change in the Brazilian Amazon , 1995 .

[38]  Russell G. Congalton,et al.  Using thematic mapper imagery to examine forest understory , 1990 .

[39]  The dynamics of temperate bamboo forests and panda conservation in China , 1997 .

[40]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .