Multi-temporal hyperspectral mixture analysis and feature selection for invasive species mapping in rainforests

被引:130
作者
Somers, Ben [1 ]
Asner, Gregory P. [2 ]
机构
[1] Flemish Inst Technol Res VITO, Ctr Remote Sensing & Earth Observat Proc TAP, BE-2400 Mol, Belgium
[2] Carnegie Inst Sci, Dept Global Ecol, Stanford, CA 94305 USA
基金
美国国家科学基金会;
关键词
MESMA; Stable Zone Unmixing; Hyperion; Time series analysis; Unmixing; Spectroscopy; Morella faya; Phenology; Hawaii; BIOLOGICAL INVASION; REFLECTANCE VARIABILITY; IMAGING SPECTROSCOPY; MYRICA-FAYA; VEGETATION; HYPERION; IMAGERY; SOILS; CLASSIFICATION; IDENTIFICATION;
D O I
10.1016/j.rse.2013.04.006
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
We evaluated the potential of a multi-temporal Multiple Endmember Spectral Mixture Analysis (MESMA) for invasive species mapping in Hawaiian rainforests. Earth Observing-1 Hyperion time series data were compiled in a single image cube and ingested into MESMA. While the temporal analysis provided a way to incorporate species phenology, a feature selection technique automatically identified the best time and best spectral feature set to optimize the separability among the native and invasive tree species in our study area. We initiated an alternative Separability Index (SI)-based feature selection approach in which a boundary condition reduced the amount of correlation in the selected spectral subset. We hypothesized that redundant spectral information could be avoided, and improved plant detection accuracy could be achieved, with reduced computational time due to the selection of fewer bands in the mixture analysis. Our analysis showed a systematic increase in the invasive species detection success when we compared the output of multi-temporal MESMA (Kappa = 0.78) with that of the traditional unitemporal approach (Kappa = 0.51-0.69). Even for unitemporal MESMA, in which only a single input image was used, the band selection strategy was beneficial both in plant detection accuracy and computational time. We could further demonstrate that, despite a lack of imagery covering all phenological events, a proper band selection strategy can emphasize subtle spectral and phenological differences between species and can thereby partly compensate for this lack of data. This creates opportunities for mapping in areas where cloud cover is a limiting factor for building extended spectral image time series. This approach is sufficiently general and inherently adaptive, thereby supporting species mapping using Hyperion and forthcoming space-borne imaging spectrometers. (C) 2013 Elsevier Inc. All rights reserved.
引用
收藏
页码:14 / 27
页数:14
相关论文
共 43 条
[1]  
Armstrong RW., 1983, Atlas of Hawaii, V2nd edn
[2]   Remote analysis of biological invasion and biogeochemical change [J].
Asner, GP ;
Vitousek, PM .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2005, 102 (12) :4383-4386
[3]   Imaging spectroscopy for desertification studies: Comparing AVIRIS and EO-1 Hyperion in Argentina drylands [J].
Asner, GP ;
Heidebrecht, KB .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (06) :1283-1296
[4]   A biogeophysical approach for automated SWIR unmixing of soils and vegetation [J].
Asner, GP ;
Lobell, DB .
REMOTE SENSING OF ENVIRONMENT, 2000, 74 (01) :99-112
[5]   Impact of tissue, canopy, and landscape factors on the hyperspectral reflectance variability of arid ecosystems [J].
Asner, GP ;
Wessman, CA ;
Bateson, CA ;
Privette, JL .
REMOTE SENSING OF ENVIRONMENT, 2000, 74 (01) :69-84
[6]   Remote sensing of native and invasive species in Hawaiian forests [J].
Asner, Gregory P. ;
Jones, Matthew O. ;
Martin, Roberta E. ;
Knapp, David E. ;
Hughes, R. Flint .
REMOTE SENSING OF ENVIRONMENT, 2008, 112 (05) :1912-1926
[7]   Invasive species detection in Hawaiian rainforests using airborne imaging spectroscopy and LiDAR [J].
Asner, Gregory P. ;
Knapp, David E. ;
Kennedy-Bowdoin, Ty ;
Jones, Matthew O. ;
Martin, Roberta E. ;
Boardman, Joseph ;
Hughes, R. Flint .
REMOTE SENSING OF ENVIRONMENT, 2008, 112 (05) :1942-1955
[8]   Vegetation-climate interactions among native and invasive species in Hawaiian rainforest [J].
Asner, Gregory P. ;
Martin, Roberta E. ;
Carlson, Kimberly M. ;
Rascher, Uwe ;
Vitousek, Peter M. .
ECOSYSTEMS, 2006, 9 (07) :1106-1117
[9]   Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales [J].
Clark, ML ;
Roberts, DA ;
Clark, DB .
REMOTE SENSING OF ENVIRONMENT, 2005, 96 (3-4) :375-398
[10]   Using vegetation reflectance variability for species level classification of hyperspectral data [J].
Cochrane, MA .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2000, 21 (10) :2075-2087