Assessment of regression kriging for spatial interpolation – comparisons of seven GIS interpolation methods

As an important GIS function, spatial interpolation is one of the most often used geographic techniques for spatial query, spatial data visualization, and spatial decision-making processes in GIS and environmental science. However, less attention has been paid on the comparisons of available spatial interpolation methods, although a number of GIS models including inverse distance weighting, spline, radial basis functions, and the typical geostatistical models (i.e. ordinary kriging, universal kriging, and cokriging) are already incorporated in GIS software packages. In this research, the conceptual and methodological aspects of regression kriging and GIS built-in interpolation models and their interpolation performance are compared and evaluated. Regression kriging is the combination of multivariate regression and kriging. It takes into consideration the spatial autocorrelation of the variable of interest, the correlation between the variable of interest and auxiliary variables (e.g., remotely sensed images are often relatively easy to obtain as auxiliary variables), and the unbiased spatial estimation with minimized variance. To assess the efficiency of regression kriging and the difference between stochastic and deterministic interpolation methods, three case studies with strong, medium, and weak correlation between the response and auxiliary variables are compared to assess interpolation performances. Results indicate that regression kriging has the potential to significantly improve spatial prediction accuracy even when using a weakly correlated auxiliary variable.     

Context-dependent spatial analysis: A role for GIS?

The relationship between spatial analysis and GIS has been a debating point for over a decade. Some see GIS as leading the way to a new era in which the desire and the ability to analyse spatial data is widespread, not just in geography but throughout all disciplines in which spatial data are encountered. Others see GIS as simply providing a medium for the recycling of out-dated spatial analytical techniques and models. This paper describes a role for GIS through the development of new forms of ‘local’ or ‘context-dependent’ spatial analytical methods in which the focus is on exceptions to the general trend represented by the more traditional ‘global’ methods.     

Object-oriented semantic labelling of spectral–spatial LiDAR point cloud for urban land cover classification and buildings detection

The urban land cover mapping and automated extraction of building boundaries is a crucial step in generating three-dimensional city models. This study proposes an object-based point cloud labelling technique to semantically label light detection and ranging (LiDAR) data captured over an urban scene. Spectral data from multispectral images are also used to complement the geometrical information from LiDAR data. Initial object primitives are created using a modified colour-based region growing technique. Multiple classifier system is then applied on the features extracted from the segments for classification and also for reducing the subjectivity involved in the selection of classifier and improving the precision of the results. The proposed methodology produces two outputs: (i) urban land cover classes and (ii) buildings masks which are further reconstructed and vectorized into three-dimensional buildings footprints. Experiments carried out on three airborne LiDAR datasets show that the proposed technique successfully discriminates urban land covers and detect urban buildings.     

A spatial–temporal Hopfield neural network approach for super-resolution land cover mapping with multi-temporal different resolution remotely sensed images

The mixed pixel problem affects the extraction of land cover information from remotely sensed images. Super-resolution mapping (SRM) can produce land cover maps with a finer spatial resolution than the remotely sensed images, and reduce the mixed pixel problem to some extent. Traditional SRMs solely adopt a single coarse-resolution image as input. Uncertainty always exists in resultant fine-resolution land cover maps, due to the lack of information about detailed land cover spatial patterns. The development of remote sensing technology has enabled the storage of a great amount of fine spatial resolution remotely sensed images. These data can provide fine-resolution land cover spatial information and are promising in reducing the SRM uncertainty. This paper presents a spatial–temporal Hopfield neural network (STHNN) based SRM, by employing both a current coarse-resolution image and a previous fine-resolution land cover map as input. STHNN considers the spatial information, as well as the temporal information of sub-pixel pairs by distinguishing the unchanged, decreased and increased land cover fractions in each coarse-resolution pixel, and uses different rules in labeling these sub-pixels. The proposed STHNN method was tested using synthetic images with different class fraction errors and real Landsat images, by comparing with pixel-based classification method and several popular SRM methods including pixel-swapping algorithm, Hopfield neural network based method and sub-pixel land cover change mapping method. Results show that STHNN outperforms pixel-based classification method, pixel-swapping algorithm and Hopfield neural network based model in most cases. The weight parameters of different STHNN spatial constraints, temporal constraints and fraction constraint have important functions in the STHNN performance. The heterogeneity degree of the previous map and the fraction images errors affect the STHNN accuracy, and can be served as guidances of selecting the optimal STHNN weight parameters.     

Remote sensing and social sensing for socioeconomic systems: A comparison study between nighttime lights and location-based social media at the 500 m spatial resolution

With the advent of “social sensing” in the Big Data era, location-based social media (LBSM) data are increasingly used to explore anthropogenic activities and their impacts on the environment. This study converts a typical kind of LBSM data, geo-tagged tweets, into raster images at the 500 m spatial resolution and compares them with the new generation nighttime lights (NTL) image products, the Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) monthly image composites. The results show that the monthly tweet images are significantly correlated with the VIIRS-DNB images at the pixel level. The tweet images have nearly the same ability on estimating electric power consumption and better performance on assessing personal incomes and population than the NTL images. Tweeted areas (i.e. the pixels with at least one posted tweet) are closer to satellite-derived built-up/urban areas than lit areas in NTL imagery, making tweet images an alternative to delimit extents of human activities. Moreover, the monthly tweet images do not show apparent seasonal changes, and the values of tweet images are more stable across different months than VIIRS-DNB monthly image composites. This study explores the potential of LBSM data at relatively fine spatiotemporal resolutions to estimate or map socioeconomic factors as an alternative to NTL images in the United States.     

How many samples are needed? An investigation of binary logistic regression for selective omission in a road network

ABSTRACT

Selective omission in a road network (or road selection) means to retain more important roads, and it is a necessary operator to transform a road network at a large scale to that at a smaller scale. This study discusses the use of the supervised learning approach to road selection, and investigates how many samples are needed for a good performance of road selection. More precisely, the binary logistic regression is employed and three road network data with different sizes and different target scales are involved for testing. The different percentages and numbers of strokes are randomly chosen for training a logistic regression model, which is further applied into the untrained strokes for validation. The performances of using the different sample sizes are mainly evaluated by an error rate estimate. Significance tests are also employed to investigate whether the use of different sample sizes shows statistically significant differences. The experimental results show that in most cases, the error rate estimate is around 0.1–0.2; more importantly, only a small number (e.g., 50–100) of training samples is needed, which indicates the usability of binary logistic regression for road selection.