Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales

By Matthew L. Clark, Dar A. Roberts, David B. Clark. 2005

785 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/f0f4458e1b42ebcb7a35b7406eee9c5ea20a769e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecological Modeling

In Ecology

In Global and Planetary Change

Citations in the corpus

Remote sensing methods for power line corridor surveys (2016, background): “However, in other environments, more studies can be found, for example, on tree delineation and tree species classification (see, e.g., Clark et al., 2005; Bunting and Lucas, 2006).”
Urban tree species mapping using hyperspectral and lidar data fusion (2014, methodology): “In a given AVIRIS pixel there is further within-class spectral variability driven by canopy architecture, exposure of woody biomass, and exposure of underlying substrate (Asner et al., 2008; Clark et al., 2005; Roberts et al., 2004).”
Spectral discrimination of healthy and Ganoderma-infected oil palms from hyperspectral data (2011, methodology): “The maximum likelihood approach was chosen because it has been widely used in many studies involving hyperspectral data (Held et al. 2003, Clark et al. 2005, Salem et al. 2005, Chen et al. 2007, Gagnon et al. 2007, Lu et al. 2007, Jollineau and Howarth 2008, Yang et al. 2009).”
Hyperspectral discrimination of tropical dry forest lianas and trees: Comparative data reduction approaches at the leaf and canopy levels (2007, neutral): “Our results contrast with those presented by Clark et al. (2005) when comparing wavelengths, which in the case of Clark et al. (2005) was aimed to separate among leaves of different tropical wet forest species.”
NEON: the first continental-scale ecological observatory with airborne remote sensing of vegetation canopy biochemistry and structure (2009, background): “capability for discriminating tropical and temperate tree species [20,21] and the discrimination of senesced plant materials, wood, or bark from background soils.”
Potential of remote sensing to predict species invasions (2015, methodology): “…Duda and Hart, 1973) using discriminant functions for each class based on the within-class covariance matrix; or iv) the spectral angle mapper (SAM; e.g. Clark et al., 2005), which is a spectral matching technique comparing each sample spectrum with several reference spectra (Kruse et al., 1993).”
Automated mapping of tropical deforestation and forest degradation: CLASlite (2009, background): “Similarly, the spectral reflectance properties of tropical forests are largely driven by species composition, as many species express variation in chemical and structural characteristics [14, 15].”
Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data (2012, methodology): “The advantage of classifying crown objects instead of individual pixels (both sunlit) corresponds to the findings in [5,10,38,39].”
Observing Changing Ecological Diversity in the Anthropocene (2013, background): “…(F) CASI, other 1.0-3.0 Belluco et al. (2006) Temperate wetlands (S) HyMap 3.0 Lucas and Carter (2008) Tropical broadleaf forest (S) HYDICE 1.6 Clark et al. (2005) Tropical broadleaf forest (F) EO-1 Hyperion 30.0 Papeş et al. (2010) Tropical lowland-to-montane rainforest (S,I) AVIRIS 3.0…”
Trends in Automatic Individual Tree Crown Detection and Delineation - Evolution of LiDAR Data (2016, background): “[27] realized that crown structure will influence the spatial covariance structure of the spectral information in each crown, but this spatial component is typically not included in spectral-based analysis.”
Differentiating plant species within and across diverse ecosystems with imaging spectroscopy (2015, methodology): “As such, these instruments have been used successfully to discriminate among plant species and functional types using leaf-level observations (Castro-Esau, Sanchez-Azofeifa, & Caelli, 2004; Clark et al., 2005), field-collected canopy spectra (Gong, Pu, & Yu, 1997; Pu, 2009), and image data (Martin, ”
Segmented canonical discriminant analysis of in situ hyperspectral data for identifying 13 urban tree species (2011, methodology): “Clark et al. (2005) conducted a hyperspectral discrimination of seven tropical rain forest tree species with the HYperspectral Digital Imagery Collection Experiment (HYDICE; spatial resolution 1.6 m) at the pixel scale with an overall accuracy of 88%. van Aadrt and Wynne (2007) mapped three…”
Mapping two Eucalyptus subgenera using multiple endmember spectral mixture analysis and continuum-removed imaging spectrometry data (2011, background): “However, vegetation types that have a high degree of spectral and structural similarity or high intra-species variability present an ongoing challenge for accurate classification andmapping (Clark et al., 2005; Cochrane, 2000; Goodwin et al., 2005; Hestir et al., 2008).”
Airborne spectranomics: mapping canopy chemical and taxonomic diversity in tropical forests (2009, background): “Canopy richness mapping works in lowland Hawai`i because the spectral signatures of the plants differ more among species than within species (Asner et al. 2008), as has been determined in other tropical forest settings (Cochrane 2000; Clark et al. 2005).”