This paper examines subset selection for nonlinear least squares parameter estimation, and applies the methodology to a test system previously studied in the power system literature, involving the on-line identification of a synchronous generator model with many parameters. Subset selection partitions the parameters into well-conditioned and ill-conditioned subsets. We show for the test system that fixing the ill-conditioned parameters to prior estimates (even if these prior estimates are substantially in error), and estimating only the remaining parameters, significantly improves the performance of the estimation algorithm and greatly enhances the quality of the estimated parameters. It is shown that attempts to estimate all of the model parameters, as done in the original work with this test system, can yield extremely unreliable results.

This paper presents a nonlinear controller for a heating, ventilating, and air conditioning (HVAC) system capable of maintaining comfort conditions under time varying thermal loads. The controller consist of a regulator and a disturbance rejection component designed using Lyapunov stability theory. The mitigation of the effect of thermal loads other than design loads on the system is due to an online thermal load and state estimator. The availability of the thermal load estimates allows the controller to keep comfort regardless of the thermal loads affecting the thermal space being heated or cooled. Simulation results are used to demonstrate the potential for keeping comfort and saving energy of this methodology on a variable-air-volume HVAC system operating on cooling mode.

This paper presents an analysis and a comparison of different linear unsupervised feature-extraction methods applied to hyperdimensional data and their impact on classification. The dimensionality reduction methods studied are under the category of unsupervised linear transformations: principal component analysis, projection pursuit (PP), and band subset selection. Special attention is paid to an optimized version of the PP introduced in this paper: optimized information divergence PP, which is the maximization of the information divergence between the probability density function of the projected data and the Gaussian distribution. This paper is particularly relevant with current and the next generation of hyperspectral sensors that acquire more information in a higher number of spectral channels or bands when compared to multispectral data. The process to uncover these high-dimensional data patterns is not a simple one. Challenges such as the Hughes phenomenon and the curse of dimensionality have an impact in high-dimensional data analysis. Unsupervised feature extraction, implemented as a linear projection from a higher dimensional space to a lower dimensional subspace, is a relevant process necessary for hyperspectral data analysis due to its capacity to overcome some difficulties of high-dimensional data. An objective of unsupervised feature extraction in hyperspectral data analysis is to reduce the dimensionality of the data maintaining its capability to discriminate data patterns of interest from unknown cluttered background that may be present in the data set. This paper presents a study of the impact these mechanisms have in the classification process. The impact is studied for supervised classification even on the conditions of a small number of training samples and unsupervised classification where unknown structures are to be uncovered and detected

Observing the environment in the vast regions of Earth through remote sensing platforms provides the tools to measure ecological dynamics. The Arctic tundra biome, one of the largest inaccessible terrestrial biomes on Earth, requires remote sensing across multiple spatial and temporal scales, from towers to satellites, particularly those equipped for imaging spectroscopy (IS). We describe a rationale for using IS derived from advances in our understanding of Arctic tundra vegetation communities and their interaction with the environment. To best leverage ongoing and forthcoming IS resources, including National Aeronautics and Space Administration’s Surface Biology and Geology mission, we identify a series of opportunities and challenges based on intrinsic spectral dimensionality analysis and a review of current data and literature that illustrates the unique attributes of the Arctic tundra biome. These opportunities and challenges include thematic vegetation mapping, complicated by low‐stature plants and very fine‐scale surface composition heterogeneity; development of scalable algorithms for retrieval of canopy and leaf traits; nuanced variation in vegetation growth and composition that complicates detection of long‐term trends; and rapid phenological changes across brief growing seasons that may go undetected due to low revisit frequency or be obscured by snow cover and clouds. We recommend improvements to future field campaigns and satellite missions, advocating for research that combines multi‐scale spectroscopy, from lab studies to satellites that enable frequent and continuous long‐term monitoring, to inform statistical and biophysical approaches to model vegetation dynamics.

This paper presents the analysis of a time series of hyperspectral images collected with the Hyperion sensor on board EO-1 to demonstrate how hyperspectral imaging can be used for studying seasonal variations of vegetation cover over the Guánica Dry Forest in Puerto Rico. The approach is based on a local unmixing procedure that splits the hyperspectral scene into tiles and performs endmember extraction on each tile. The main assumption is that within a tile, a single spectral signature is an adequate representation of an endmember. Local endmember signatures from each tile are then clustered to extract endmember classes that better account for endmember spectral variability across the scene and provide a better global description of the full forest scene. Within a scene, abundances are computed using all extracted spectral endmembers and the abundance of an endmember class is computed as the sum of the abundances for the spectral endmembers belonging to that class. Variations in abundance maps are used to understand seasonal changes in forest cover. The procedure was performed using eleven near-cloud-free Hyperion images collected in different months in 2008. Results from the analysis agreed with published knowledge of the phenological changes for this forest. Correlation analyses with NDVI and rainfall time series are used to understand variations in coverage of certain endmember classes with weather. Mangrove was shown to be uncorrelated with rainfall, whereas the upland forest endmember was highly correlated with rain. This study shows the potential for unmixing methods to exploit hyperspectral data for temporal analysis.