Conference Paper

Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems

DOI: 10.1117/12.849882 Conference: , Laser Radar Technology and Applications XV

ABSTRACT

Research groups at Rochester Institute of Technology and Carnegie Institution for Science are studying savanna ecosystems and are using data from the Carnegie Airborne Observatory (CAO), which integrates advanced imaging spectroscopy and waveform light detection and ranging (wLIDAR) data. This component of the larger ecosystem project has as a goal the fusion of imaging spectroscopy and wLIDAR data in order to improve per-species structural parameter estimation. Waveform LIDAR has proven useful for extracting high vertical resolution structural parameters, while imaging spectroscopy is a well-established tool for species classification. We evaluated data fusion at the feature level, using a stepwise discrimination analysis (SDA) approach with feature metrics from both hyperspectral imagery (HSI) and wLIDAR data. It was found that fusing data with the SDA improved classification, although not significantly. The principal component analysis (PCA) provided many useful bands for the SDA selection, both from HSI and wLIDAR. The overall classification accuracy was 68% for wLIDAR, 59% for HSI, and 72% for the fused data set. The kappa accuracy achieved with wLIDAR was 0.49, 0.36 for HSI, and 0.56 for both modalities.

Download full-text

Full-text

Available from: Gregory P. Asner, Jan 03, 2016
  • Source
    • "However, little research has been performed on species-level classification using both HSI and wLiDAR. Sarrazin et al. (2010) performed exploratory species-level classification using wLiDAR and HSI. They deconvolved the wLiDAR data, corrected data for topographic variation, and extracted structural and spectral features from each modality. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The mapping of tree species, in general and specifically in diverse savanna environments, is of great interest to ecologists and natural resource managers. This study focused on the fusion of imaging spectroscopy and small footprint waveform light detection and ranging (wLiDAR) data to improve per species structural parameter estimation towards classification and herbaceous biomass modeling. The species classification approach was based on stepwise discriminant analysis (SDA) and used feature metrics from hyperspectral imagery (HSI) combined with wLiDAR data. It was found that fusing data with the SDA did not improve classification significantly, especially compared with the HSI classification results. As for herbaceous biomass modeling, the statistical approach used for the fusion of wLiDAR and HSI was forward selection regression modeling, which selects significant independent metrics and models those to measured biomass. The results indicated that fine scale wLiDAR may not be able to provide accurate measurement of herbaceous biomass, although other factors could have contributed to the relatively poor results, such as the senescent state of grass, the narrow biomass range that was measured, and the low biomass values, i.e., the limited laser-target interactions. We concluded that although fusion did not result in significant improvements over single modality approaches in these two use cases, there is a need for further investigation during the peak growing season.
    Full-text · Article · Dec 2011
  • Source
    • "However, little research has been performed on species-level classification using both HSI and wLiDAR. Sarrazin et al. (2010) performed exploratory species-level classification using wLiDAR and HSI. They deconvolved the wLiDAR data, corrected data for topographic variation, and extracted structural and spectral features from each modality. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The mapping of tree species, in general and specifically in diverse savanna environments, is of great interest to ecologists and natural resource managers. This study focused on the fusion of imaging spectroscopy and small-footprint waveform light detection and ranging (wLiDAR) data to improve per species structural parameter estimation towards classification and herbaceous biomass modeling. The species classification approach was based on stepwise discriminant analysis (SDA) and used feature metrics from hyperspectral imagery (HSI) combined with wLiDAR data. It was found that fusing data with the SDA did not improve classification significantly, especially compared with the HSI classification results. As for herbaceous biomass modeling, the statistical approach used for the fusion of wLiDAR and HSI was forward selection regression modeling, which selects significant independent metrics and models those to measured biomass. The results indicated that fine scale wLiDAR may not be able to provide accurate measurement of herbaceous biomass, although other factors could have contributed to the relatively poor results, such as the senescent state of grass, the narrow biomass range that was measured, and the low biomass values, i.e., the limited laser-target interactions. We concluded that although fusion did not result in significant improvements over single modality approaches in these two use cases, there is a need for further investigation during the peak growing season.
    Full-text · Article · Dec 2011 · Canadian Journal of Remote Sensing
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Mapping savanna tree species is of broad interest for savanna ecology and rural resource inventory. We investigated the utility of (i) the Carnegie Airborne Observatory (CAO) hyperspectral data, and WorldView-2 and Quickbird multispectral spectral data and (ii) a combined spectral + tree height dataset (derived from the CAO LiDAR system) for mapping seven common savanna tree species or genera in the Sabi Sands Reserve and communal lands adjacent to Kruger National Park, South Africa. We convolved the 72 spectral bands of the CAO imagery to eight and four multispectral channels available in the WorldView-2 and Quickbird satellite sensors, respectively. A combination of the simulated WorldView-2 data and LiDAR tree height imagery was also assessed for species classification. First, the simulated WorldView-2 imagery provided a higher classification accuracy (77% ± 3.1 (mean ± standard deviation)) when compared to the simulated Quickbird (65% ± 1.9) and CAO (65% ± 1.2) data. Secondly, the combined spectral + height dataset provided a slightly higher overall classification accuracy (79% ± 1.8) when compared to the WorldView-2 spectral only dataset. The difference was however, statistically significant (p < 0.001; one-way analysis of variance for 30 bootstrapped replicates (n = 100) of the independent validation dataset). Higher classification accuracies were observed for trees with large crowns such as S. birrea, S. africana and A. nigrescens as compared to trees with small crowns. Species composition and diversity maps of trees with large crowns were consistent with established knowledge in the area. For example, the results showed higher tree diversity (number of different species per ha) in the Sabi Sands game reserve than in the communal areas. This study highlights the feasibility of remote sensing of tree species at the landscape scale in African savannas and the potential applicability of WorldView-2 sensor in mapping savanna tree species with a large crown.
    Full-text · Article · Oct 2012 · Remote Sensing of Environment
Show more