This article compares four new automatic methods to discriminate between spruce, pine and birch, which are the dominating tree species in Norwegian forests. Airborne laser scanning and hyperspectral data were used. The laser scanning data was used to mask pixels with low or no vegetation in the hyperspectral data. A green-blue ratio was used to remove shadow areas from tree canopies, and the normalized difference vegetation index to remove dead vegetation and non-vegetation. The best method was hyperspectral pixel classification with 160 spectral channels in the visible and near-infrared spectrum, using a deep neural network. This method achieved 87% correct classification rate. Partial least squares regression for hyperspectral pixel classification achieved 78%. Deep neural network image classification using canopy height blended with three hyperspectral channels achieved 74%. A simple pixel classification method based on two spectral indices resulted in 67% correct classification. A possible future improvement is to find a better way to combine hyperspectral data with canopy height data in a deep neural network.
ARTICLE HISTORY
2014) Impact of satellite-based lake surface observations on the initial state of HIRLAM. Part I: evaluation of remotely-sensed lake surface water temperature observations, Tellus A: Dynamic Meteorology and Oceanography, 66:1, 21534, A B S T R A C T Lake Surface Water Temperature (LSWT) observations are used to improve the lake surface state in the High Resolution Limited Area Model (HIRLAM), a three-dimensional numerical weather prediction (NWP) model. In this paper, satellite-derived LSWT observations from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Along-Track Scanning Radiometer (AATSR) are evaluated against in-situ measurements collected by the Finnish Environment Institute (SYKE) for a selection of large-to medium-size lakes during the open-water season. Data assimilation of these LSWT observations into the HIRLAM is in the paper Part II. Results show a good agreement between MODIS and in-situ measurements from 22 Finnish lakes, with a mean bias of (1.138C determined over five open-water seasons (2007Á2011). Evaluation of MODIS during an overlapping period (2007Á2009) with the AATSR-L2 product currently distributed by the European Space Agency (ESA) shows a mean (cold) bias error of (0.938C for MODIS and a warm mean bias of 1.088C for AATSR-L2. Two additional LSWT retrieval algorithms were applied to produce more accurate AATSR products. The algorithms use ESA's AATSR-L1B brightness temperature product to generate new L2 products: one based on Key et al. (1997) and the other on Prata (2002) with a finer resolution water mask than used in the creation of the AATSR-L2 product distributed by ESA. The accuracies of LSWT retrievals are improved with the Key and Prata algorithms with biases of 0.788C and (0.118C, respectively, compared to the original AATSR-L2 product (3.188C).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.