Title :
Monitoring plant invasions in Hawaiian rainforests through multi-temporal unmixing
Author :
Ben, Somers ; Asner, Gregory P.
Author_Institution :
Dept. of Earth & Environ. Sci., Katholieke Univ. Leuven, Leuven, Belgium
Abstract :
We evaluated the potential of a multi-temporal MESMA for invasive species mapping in Hawaiian rainforests. EO-1 Hyperion data were compiled in a single image cube and ingested into MESMA. The temporal analysis provided a way to incorporate species phenology meanwhile a feature selection technique automatically identified the best time and best feature set to optimize the separability among the target tree species. Our analysis showed a systematic increase in the invasive species detection success when compared to the output of the traditional unitemporal approach (Kappa = 0.69 vs 0.78).
Keywords :
remote sensing; vegetation; EO-1 Hyperion data; Hawaiian rainforests; feature selection technique; invasive species detection; invasive species mapping; multitemporal MESMA potential; multitemporal unmixing; plant invasion monitoring; single image cube; species phenology; target tree species; temporal analysis; Hyperspectral imaging; Libraries; Monitoring; Spatial resolution; Time series analysis; Vegetation; MESMA; biodiversity; hyperspectral; vegetation;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Conference_Location :
Quebec City, QC
DOI :
10.1109/IGARSS.2014.6947343
