Geospatial data mining for digital raster mapping

We performed an in-depth literature survey to identify the most popular data mining approaches that have been applied for raster mapping of ecological parameters through the use of Geographic Information Systems (GIS) and remotely sensed data. Popular data mining approaches included decision trees or “data mining” trees which consist of regression and classification trees, random forests, neural networks, and support vector machines. The advantages of each data mining approach as well as approaches to avoid overfitting are subsequently discussed. We also provide suggestions and examples for the mapping of problematic variables or classes, future or historical projections, and avoidance of model bias. Finally, we address the separate issues of parallel processing, error mapping, and incorporation of “no data” values into modeling processes. Given the improved availability of digital spatial products and remote sensing products, data mining approaches combined with parallel processing potentials should greatly improve the quality and extent of ecological datasets.     

A literature synthesis of LiDAR applications in transportation: feature extraction and geometric assessments of highways

Interest in using Light Detection and Ranging (LiDAR) technology in Transportation Engineering has grown over the past decade. The high accuracy of LiDAR datasets and the efficiency by which they can be collected has led many transportation agencies to consider mobile LiDAR as an alternative to conventional tools when surveying roadway infrastructure. Nonetheless, extracting semantic information from LiDAR datasets can be extremely challenging. Although extracting roadway features from LiDAR has been considered in previous research, the extraction of some features has received more attention than others. In fact, for some roadway design elements, attempts to extract those elements from LiDAR have been extremely scarce. To document the research that has been done in this area, this paper conducts a thorough review of existing studies while also highlighting areas where more research is required. Unlike previous research, this paper includes a thorough review of the previous attempts at data extraction from LiDAR while summarizing the detailed steps of the extraction procedure proposed in each study. Moreover, the paper also identifies common tools and techniques used to extract information from LiDAR for transportation applications. The paper also highlights common limitations in existing algorithms that could be improved in future research. This paper represents a valuable resource for researchers and practitioners interested in knowing the current state of research on the applications of LiDAR in the field of Transportation Engineering while also understanding the opportunities and challenges that lie ahead.     

Finding and sharing GIS methods based on the questions they answer

Geographic information has become central for data scientists of many disciplines to put their analyzes into a spatio-temporal perspective. However, just as the volume and variety of data sources on the Web grow, it becomes increasingly harder for analysts to be familiar with all the available geospatial tools, including toolboxes in Geographic Information Systems (GIS), R packages, and Python modules. Even though the semantics of the questions answered by these tools can be broadly shared, tools and data sources are still divided by syntax and platform-specific technicalities. It would, therefore, be hugely beneficial for information science if analysts could simply ask questions in generic and familiar terms to obtain the tools and data necessary to answer them. In this article, we systematically investigate the analytic questions that lie behind a range of common GIS tools, and we propose a semantic framework to match analytic questions and tools that are capable of answering them. To support the matching process, we define a tractable subset of SPARQL, the query language of the Semantic Web, and we propose and test an algorithm for computing query containment. We illustrate the identification of tools to answer user questions on a set of common user requests.     

Geomasking sensitive health data and privacy protection: an evaluation using an E911 database

Geomasking is used to provide privacy protection for individual address information while maintaining spatial resolution for mapping purposes. Donut geomasking and other random perturbation geomasking algorithms rely on the assumption of a homogeneously distributed population to calculate displacement distances, leading to possible under-protection of individuals when this condition is not met. Using household data from 2007, we evaluated the performance of donut geomasking in Orange County, North Carolina. We calculated the estimated k-anonymity for every household based on the assumption of uniform household distribution. We then determined the actual k-anonymity by revealing household locations contained in the county E911 database. Census block groups in mixed-use areas with high population distribution heterogeneity were the most likely to have privacy protection below selected criteria. For heterogeneous populations, we suggest tripling the minimum displacement area in the donut to protect privacy with a less than 1% error rate.     

Towards Real‐Time Geodemographics: Clustering Algorithm Performance for Large Multidimensional Spatial Databases

Geodemographic classifications provide discrete indicators of the social, economic and demographic characteristics of people living within small geographic areas. They have hitherto been regarded as products, which are the final “best” outcome that can be achieved using available data and algorithms. However, reduction in computational cost, increased network bandwidths and increasingly accessible spatial data infrastructures have together created the potential for the creation of classifications in near real time within distributed online environments. Yet paramount to the creation of truly real time geodemographic classifications is the ability for software to process and efficiency cluster large multidimensional spatial databases within a timescale that is consistent with online user interaction. To this end, this article evaluates the computational efficiency of a number of clustering algorithms with a view to creating geodemographic classifications “on the fly” at a range of different geographic scales.     

The Landscape of GIScience Publications 1997–2007: An Empirical Investigation with Latent Semantic Analysis

This article reports on an empirical study of the trends and patterns of research activities in Geographic Information Science (GIScience) during the years 1997–2007. The GIScience research priorities identified by the University Consortium of Geographic Information Science (UCGIS) were used as guidelines to examine the 985 research articles published in six well‐recognized academic journals. Latent Semantic Analysis (LSA) was employed to investigate the association among the different GIScience research themes. The spatial and temporal patterns of the association between the publications and the different GIScience themes were examined to show the development of GIScience research during the study period. Furthermore, correlation analyses between the publications were conducted following the LSA results to reveal GIScience research networks, including the networks of the published articles and those formed by the research places. In this article, we applied an approach that was developed within information science to depict what GIS research activities were conducted when and where and how they connect to each other through sharing common research themes. The related findings pave the way for future efforts to describe the paradigm of GIScience as well as the pattern of GIScience research.     

A first look at the effects of ionospheric signal bending on a globally processed GPS network

This study provides a first attempt at quantifying potential signal bending effects on the GPS reference frame, coordinates and zenith tropospheric delays (ZTDs). To do this, we homogeneously reanalysed data from a global network of GPS sites spanning 14 years (1995.0–2009.0). Satellite, Earth orientation, tropospheric and ground station coordinate parameters were all estimated. We tested the effect of geometric bending and dTEC bending corrections, which were modelled at the observation level based, in part, on parameters from the International Reference Ionosphere 2007 model. Combined, the two bending corrections appear to have a minimal effect on site coordinates and ZTDs except for low latitude sites. Considering five days (DOY 301–305, 28 October–1 November 2001) near ionospheric maximum in detail, they affect mean ZTDs by up to ~1.7 mm at low latitudes, reducing to negligible levels at high latitudes. Examining the effect on coordinates in terms of power-spectra revealed the difference to be almost entirely white noise, with noise amplitude ranging from 0.3 mm (high latitudes) to 2.4 mm (low latitudes). The limited effect on station coordinates is probably due to the similarity in the elevation dependence of the bending term with that of tropospheric mapping functions. The smoothed z-translation from the GPS reference frame to ITRF2005 changes by less than 2 mm, though the effect combines positively with that from the second order ionospheric refractive index term. We conclude that, at the present time, and for most practical purposes, the geometric and dTEC bending corrections are probably negligible at current GPS/reference frame precisions.     

Entropy-based fuzzy classification parameter optimization using uncertainty variation across spatial resolution

In the past researchers have suggested hard classification approaches for pure pixel remote sensing data and to handle mixed pixels soft classification approaches have been studied for land cover mapping. In this research work, while selecting fuzzy c-means (FCM) as a base soft classifier entropy parameter has been added. For this research work Resourcesat-1 (IRS-P6) datasets from AWIFS, LISSIII and LISS-IV sensors of same date have been used. AWIFS and LISS-III datasets have been used for classification and LISS-III and LISS-IV data were used for reference data generation, respectively. Soft classified outputs from entropy based FCM classifiers for AWIFS and LISS-III datasets have been evaluated using sub-pixel confusion uncertainty matrix (SCM). It has been observed that output from FCM classifier has higher classification accuracy with higher uncertainty but entropy-based classifier with optimum value of regularizing parameter generates classified output with minimum uncertainty.     

Kinematic precise point positioning at remote marine platforms

Precise kinematic differential positioning using the global positioning system (GPS) at a marine platform usually requires a relatively short distance (e.g. <500 km) to a land-based reference station. As an alternative, precise point positioning (PPP) is normally considered free from this limiting requirement. However, due to the prerequisite of network-based satellite products, PPP at a remote marine platform may still be affected by its distance to the reference network. Hence, this paper investigates this scenario by configuring rings of reference stations with different radii centered on a to-be-positioned marine platform. Particularly, we applied ambiguity resolution at a single station to PPP by estimating uncalibrated phase delays (UPDs). We used three rings of reference stations centered on a vessel, with radii of roughly 900, 2,000 and 3,600 km, to determine satellite clocks and UPDs independently. For comparison, we also performed differential positioning based on a single reference station with baseline lengths of about 400, 1,700 and 2,800 km. We demonstrate that, despite the increasing ring-network radius to a few 1,000 km, the overall change in accuracy of the satellite clocks that are used at the vessel is smaller than 0.02 ns, and the RMS values of differences between the three sets of narrow-lane UPD estimates are around 0.05 cycles only. Moreover, the kinematic positioning accuracy of PPP is affected by the increasing ring-network radius, but can still achieve several centimeters after ambiguity resolution when the vessel is over a few 1,000 km away from the ring network, showing better performance than that of differential positioning. Therefore, we propose that ambiguity-fixed PPP can be used at remote marine platforms that support precise oceanographic and geophysical applications in open oceans.