ABSTRACTMany countries have employed recently developed technologies, such as airborne lidar, to capture nationwide three-dimensional information over the past few years. In Spain, a huge volume of lidar information is available for the majority of the territory in the Spanish National Plan of Aerial Orthophotography. In this article, a multi-source approach is taken, integrating available.
DescriptionPansharpening algorithms fuse higher spatial resolution panchromatic with lower spatial resolution multispectral imagery to create higher spatial resolution multispectral images. The free-availability and systematic global acquisition of Landsat 8 data indicate an expected need for global coverage and so computationally efficient Landsat 8 pansharpening. This study adapts and evaluates the established, and relatively computationally inexpensive, Brovey and context adaptive Gram Schmidt component substitution (CS) pansharpening methods for application to the Landsat 8 15 m panchromatic and 30 m red, green, blue, and near-infrared bands. The intensity images used by these CS pansharpening methods are derived as a weighted linear combination of the multispectral bands in three different ways using band spectral weights set (i) equally as the reciprocal of the number of bands; (ii) using fixed Landsat 8 spectral response function based (SRFB) weights derived considering laboratory spectra; and (iii) using image specific spectral weights derived by regression between the multispectral and the degraded panchromatic bands.
The spatial and spectral distortion and computational cost of the different methods are assessed using Landsat 8 test images acquired over agricultural scenes in South Dakota, China, and India. The results of this study indicate that, for global Landsat 8 application, the context adaptive Gram Schmidt pansharpening with an intensity image defined using the SRFB spectral weights is appropriate. The context adaptive Gram Schmidt pansharpened results had lower distortion than the Brovey results and the least distortion was found using intensity images derived using the SRFB and image specific spectral weights but the computational cost using the image specific weights was greater than the using the SRFB weights. Recommendations for large area Landsat 8 pansharpening application are described briefly and the SRFB spectral weights are provided so users may implement computationally inexpensive Landsat 8 pansharpening themselves.
Regression methods are widely employed in forestry to predict and map structure and canopy fuel variables. We present a study where several regression models (linear, non-linear, regression trees and ensemble) were assessed. Independent variables were calculated using metrics extracted from full-waveform LiDAR data, while the reference data used to generate the dependent variables for the prediction models were obtained from fieldwork in 78 plots of 16 m radius. Transformations of dependent and independent variables with feature selection were carried out to assess their influence in the prediction of response variables.
In order to evaluate significant differences and rank regression models we used the non-parametric tests Wilcoxon and Friedman, and post-hoc analysis or post-hoc pairwise multiple comparison tests, such as Nemenyi, for Friedman test. Regressions using transformation of the dependent variable, like square-root or logarithmic, or the independent variable, increased R2 up to 6% with respect to linear regression using unprocessed response variables.
CART (Classification and Regression Tree) method provided poor results, but it may be interesting for categorisation purposes. Square-root transformation of the dependent variable is the method having the best overall results, except for stand volume. However, not always has a significant improvement with respect to other regression methods.