CyberGIS – defined as cyberinfrastructure-based geographic information systems (GIS) – has emerged as a new generation of GIS representing an important research direction for both cyberinfrastructure and geographic information science. This study introduces a 5-year effort funded by the US National Science Foundation to advance the science and applications of CyberGIS, particularly for enabling the analysis of big spatial data, computationally intensive spatial analysis and modeling (SAM), and collaborative geospatial problem-solving and decision-making, simultaneously conducted by a large number of users. Several fundamental research questions are raised and addressed while a set of CyberGIS challenges and opportunities are identified from scientific perspectives. The study reviews several key CyberGIS software tools that are used to elucidate a vision and roadmap for CyberGIS software research. The roadmap focuses on software integration and synthesis of cyberinfrastructure, GIS, and SAM by defining several key integration dimensions and strategies. CyberGIS, based on this holistic integration roadmap, exhibits the following key characteristics: high-performance and scalable, open and distributed, collaborative, service-oriented, user-centric, and community-driven. As a major result of the roadmap, two key CyberGIS modalities – gateway and toolkit – combined with a community-driven and participatory approach have laid a solid foundation to achieve scientific breakthroughs across many geospatial communities that would be otherwise impossible.

Background: The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), causing the coronavirus disease 2019 (COVID-19) pandemic, has infected millions of people and caused hundreds of thousands of deaths. While COVID-19 has overwhelmed healthcare resources (e.g., healthcare personnel, testing resources, hospital beds, and ventilators) in a number of countries, limited research has been conducted to understand spatial accessibility of such resources. This study fills this gap by rapidly measuring the spatial accessibility of COVID-19 healthcare resources with a particular focus on Illinois, USA.Method: The rapid measurement is achieved by resolving computational intensity of an enhanced two-step floating catchment area (E2SFCA) method through a parallel computing strategy based on cyberGIS (cyber geographic information science and systems). The E2SFCA has two major steps. First, it calculates a bed-to-population ratio for each hospital location. Second, it sums these ratios for residential locations where hospital locations overlap.Results: The comparison of the spatial accessibility measures for COVID-19 patients to those of population at risk identifies which geographic areas need additional healthcare resources to improve access. The results also help delineate the areas that may face a COVID-19-induced shortage of healthcare resources. The Chicagoland, particularly the southern Chicago, shows an additional need for resources. This study also identified vulnerable population residing in the areas with low spatial accessibility in Chicago.Conclusion: Rapidly measuring spatial accessibility of healthcare resources provides an improved understanding of how well the healthcare infrastructure is equipped to save people’s lives during the COVID-19 pandemic. The findings are relevant for policymakers and public health practitioners to allocate existing healthcare resources or distribute new resources for maximum access to health services.

Existing urban boundaries are usually defined by government agencies for administrative, economic, and political purposes. However, it is not clear whether the boundaries truly reflect human interactions with urban space in intra- and interregional activities. Defining urban boundaries that consider socioeconomic relationships and citizen commute patterns is important for many aspects of urban and regional planning. In this paper, we describe a method to delineate urban boundaries based upon human interactions with physical space inferred from social media. Specifically, we depicted the urban boundaries of Great Britain using a mobility network of Twitter user spatial interactions, which was inferred from over 69 million geo-located tweets. We define the non-administrative anthropographic boundaries in a hierarchical fashion based on different physical movement ranges of users derived from the collective mobility patterns of Twitter users in Great Britain. The results of strongly connected urban regions in the form of communities in the network space yield geographically cohesive, nonoverlapping urban areas, which provide a clear delineation of the non-administrative anthropographic urban boundaries of Great Britain. The method was applied to both national (Great Britain) and municipal scales (the London metropolis). While our results corresponded well with the administrative boundaries, many unexpected and interesting boundaries were identified. Importantly, as the depicted urban boundaries exhibited a strong instance of spatial proximity, we employed a gravity model to understand the distance decay effects in shaping the delineated urban boundaries. The model explains how geographical distances found in the mobility patterns affect the interaction intensity among different non-administrative anthropographic urban areas, which provides new insights into human spatial interactions with urban space.

This paper presents a theoretical approach that has been developed to capture the computational intensity and computing resource requirements of geographical data and analysis methods. These requirements are then transformed into a common framework, a grid‐based representation of a spatial computational domain, which supports the efficient use of emerging cyberinfrastructure environments. Two key types of transformational functions (data‐centric and operation‐centric) are identified and their relationships are explained. The application of the approach is illustrated using two geographical analysis methods: inverse distance weighted interpolation and the spatial statistic. We describe the underpinnings of these two methods, present their conventional sequential algorithms, and then address their latent parallelism based on a spatial computational domain representation. Through the application of this theoretical approach, the development of domain decomposition methods is decoupled from specific high‐performance computer architectures and task scheduling implementations, which makes the design of generic parallel processing solutions feasible for geographical analyses.

Deep neural networks (DNNs), which learn a hierarchical representation of features, have shown remarkable performance in big data analytics of remote sensing. However, previous research indicates that DNNs are easily spoofed by adversarial examples, which are crafted images with artificial perturbations that fool DNN models toward wrong predictions. To comprehensively evaluate the impact of adversarial examples on the remote sensing image (RSI) scene classification, this study tests eight state-of-the-art classification DNNs on six RSI benchmarks. These data sets include both optical and synthetic-aperture radar (SAR) images of different spectral and spatial resolutions. In the experiment, we create 48 classification scenarios and use four cutting-edge attack algorithms to investigate the influence of the adversarial example on the classification of RSIs. The experimental result shows that the fooling rates of the attacks are all over 98% across the 48 scenarios. We also find that, for the optical data, the seriousness of the adversarial problem has a negative relationship with the richness of the feature information. Besides, adversarial examples generated from SAR images are used easily for fooling the models with an average fooling rate of 76.01%. By analyzing the class distribution of these adversarial examples, we find that the distribution of the misclassifications is not affected by the types of models and attack algorithms-adversarial examples of RSIs of the same class cluster on fixed several classes. The analysis of classes of adversarial examples not only helps us explore the relationships between data set classes but also provides insights for further designing defensive algorithms.

Viewshed analysis, often supported by geographic information system, is widely used in many application domains. However, as terrain data continue to become increasingly large and available at high resolutions, data-intensive viewshed analysis poses significant computational challenges. General-purpose computation on graphics processing units (GPUs) provides a promising means to address such challenges. This article describes a parallel computing approach to data-intensive viewshed analysis of large terrain data using GPUs. Our approach exploits the high-bandwidth memory of GPUs and the parallelism of massive spatial data to enable memory-intensive and computation-intensive tasks while central processing units are used to achieve efficient input/output (I/O) management. Furthermore, a two-level spatial domain decomposition strategy has been developed to mitigate a performance bottleneck caused by data transfer in the memory hierarchy of GPU-based architecture. Computational experiments were designed to evaluate computational performance of the approach. The experiments demonstrate significant performance improvement over a well-known sequential computing method, and an enhanced ability of analyzing sizable datasets that the sequential computing method cannot handle.