EAGER: CISSDA: A Unified Cyberinfrastructure Framework for Scalable Spatiotemporal Data Analytics

大量的时空数据集通常使用全球定位系统（GPS）和其他位置感知设备收集。随着地理信息科学技术的不断发展，时空数据挖掘和分析变得越来越重要，为众多领域的科学调查和决策提供了支持。需要大数据和广泛的计算能力来挖掘和分析跨多个尺度收集并用于各种应用的大量复杂时空数据。然而，传统的时空数据挖掘和分析方法和工具主要是使用顺序计算开发的，不能充分处理日益增长的数据强度、复杂性和应用的多样性。只有无缝地利用异构和先进的计算和信息基础设施——网络基础设施——才能在大范围内有效地分析大量复杂的时空数据。该项目通过调整和集成计算和信息基础设施的异构模式（如云、高性能计算和高吞吐量计算），为可扩展的时空数据分析创建一个统一的网络基础设施框架。该框架包含两种新型和互补的能力：1)通过综合数据挖掘、信息网络分析、并行计算和云计算，为可扩展的时空数据分析提供一套方法和算法；2)基于先进的网络基础设施（即cyberGIS）的地理信息系统（GIS），以方便大量用户使用方法和算法。这些新功能有助于克服目前涉及大量时空数据的地理和社会科学研究的许多限制，并为制定新政策提供有用的见解。该框架旨在通过对描述个人在空间和时间上运动的大量时空轨迹数据的可扩展分析，获得对环境健康领域中个人活动模式和空间的新的基本理解。通过普遍使用时空数据，该项目将对几乎所有采用地理空间技术解决科学问题和支持决策的学科产生变革性和广泛的影响。

Massive spatiotemporal datasets are often collected using global positioning systems (GPS) and other location-aware devices. Spatiotemporal data mining and analysis have become increasingly important as continued growth in geographic information science and technology enables scientific investigations and decision-making support in a plethora of fields. Big data and extensive computational capabilities are needed to mine and analyze the massive quantities of complex spatiotemporal data collected across multiple scales and used for diverse applications. However, conventional methods and tools for spatiotemporal data mining and analysis are developed primarily using sequential computing, and cannot adequately handle this increasing data intensity, complexity, and diversity of applications. Only by seamlessly harnessing heterogeneous and advanced computing and information infrastructure - cyberinfrastructure - can large and complex spatiotemporal data be efficiently analyzed on a wide scale.This project creates a unified cyberinfrastructure framework by adapting and integrating heterogeneous modalities of computing and information infrastructure (e.g., cloud, high-performance computing, and high-throughput computing) for scalable spatiotemporal data analytics. The framework encompasses two types of novel and complementary capabilities: 1) a suite of methods and algorithms for scalable spatiotemporal data analytics through synthesis of data mining, information network analysis, and parallel and cloud computing; and 2) a geographic information system (GIS) based on advanced cyberinfrastructure (i.e., cyberGIS) to facilitate the use of the methods and algorithms by a large number of users. These novel capabilities help overcome many current limitations in geographic and social science research involving huge amount of spatiotemporal data, and bring forth useful insights for formulating new policies. The framework is designed to gain new fundamental understanding about individual activity patterns and spaces in the domain of environmental health through scalable analysis of massive space-time trajectory data that depict the movement of individuals over space and time. By the ubiquitous use of spatiotemporal data, the project will lead to both transformative and broad impacts on almost all disciplines that employ geospatial technologies for scientific problem solving and decision-making support.