1,299
Views
9
CrossRef citations to date
0
Altmetric
Forum: Context and Uncertainty in Geography and GIScience

Challenges and Prospects of Uncertainties in Spatial Big Data Analytics

, , &
Pages 1513-1520 | Received 01 Sep 2017, Accepted 01 Dec 2017, Published online: 14 Mar 2018
 

Abstract

Knowledge extraction from spatial big data (SBD) with advanced analytics has become a major trend in research and industry. Meanwhile, the increasingly complex SBD and its analytics face proliferating challenges posed by uncertainties in them. Linked to various characteristics of SBD, the uncertainties emerge and propagate in each stage of SBD analytics. To avoid unreliable knowledge and losses resulting from the uncertainties and to ensure the value of authentic knowledge, this article proposes uncertainty-based SBD analytics. Uncertainty-based SBD analytics strive to understand, control, and alleviate uncertainties and their propagation in each stage of geographic knowledge extraction. Key topics involved in uncertainty-based SBD analytics include, for example, place-based heuristics for learning urban structure and place-based analytics on broader knowledge extraction tasks; dealing with the biases and inferencing the semantics in cell phone tracking data; quality assessment of unstructured spatial user-generated contents and the rectification of location shifts and time elapses between humans' activities and corresponding online contents they generate; and uncertainty handling in sophisticated black-box analytics with SBD such as deep learning. Challenges and the latest advances in each of these topics are presented, and further research for addressing these challenges is suggested in this article.

运用先进的分析从空间大数据 (SBD) 中获取知识, 已成为研究和产业的主要趋势。于此同时, 逐渐复杂化的 SBD 及其分析, 因自身的不确定性而带来的挑战激增。不确定性与 SBD 的各种特徵相互连结, 在 SBD 分析的各阶段中浮现并增生。为了避免不确定所导致的不可靠知识与损失, 以及确保原初知识的价值, 本文提出根据不确定性的 SBD 分析。根据不确定性的 SBD 分析, 旨在理解、控制并减轻地理知识获取的各阶段中的不确定性及其增生。以不确定性为基础的 SBD 所涉及的主要主题, 包含例如学习城市结构时以空间为基础的启发法, 以及以地方为基础的更广泛的知识获取工作之分析; 应对偏见并推断手机追踪数据中的语义学; 非结构性空间使用者生产的内容的质量评估, 并矫正人类活动及其生产的相应网路内容之间的区位变异和时间经过; 以及在诸如深度学习的 SBD 之复杂黑箱分析中的不确定性处理。本文将呈现这些主题各自的挑战与最新的进展, 并提出应对这些挑战的进一步研究之建议。

La extracción de conocimiento de los big data espaciales (SDB) por medio de analíticas avanzadas se ha convertido en tendencia importante en la investigación y la industria. Mientras tanto, los cada vez más complejos SDB y sus analíticas enfrentan la proliferación de retos planteados por las incertidumbres propias de ellos. Ligadas a varias características de los SBD, las incertidumbres surgen y se propagan en cada etapa de las analíticas de los SBD. Para evitar conocimiento no confiable y las pérdidas que resultan por las incertidumbres, y para asegurar el valor del conocimiento auténtico, este artículo propone una analítica de los SBD basada en incertidumbre. La analítica de los SBD basada en incertidumbre se esfuerza en entender, controlar y paliar las incertidumbres y su propagación en cada etapa de la extracción de conocimiento geográfico. Los tópicos clave involucrados en la analítica de los SDB basada en incertidumbre incluyen, por ejemplo, la heurística basada en lugar para aprender estructura urbana y analítica basada en lugar sobre tareas más amplias de extracción de conocimiento; lidiar con los sesgos e inferencias semánticas del rastreo de datos de teléfonos celulares; evaluación de la calidad de contenidos espaciales no estructurados generados por el usuario, y la rectificación de cambios de localización y tiempos transcurridos entre las actividades de los humanos y los correspondientes contenidos online por ellos generados; y el manejo de la incertidumbre en una analítica sofisticada de caja negra con el SBD tal como la del aprendizaje profundo. En el artículo se presentan los retos y los avances más recientes en cada uno de estos tópicos, al tiempo que se sugiere más investigación para abocar aquellos retos.

Acknowledgments

We sincerely thank the editor, Professor Mei-Po Kwan, and the anonymous reviewers for their insightful comments and help on improving this article. Thanks to Pengfei Chen, Lipeng Gao, Zhewei Liu, Pan Shao, Yiling Wan, and Xiaokang Zhang for helping provide opinions and collect references for this work.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China (41331175), Minister of Science and Technology of P.R. China (2017YFB0503604), and the Hong Kong Polytechnic University (1-ZE24, 4-ZZFZ).

Notes on contributors

Wenzhong Shi

WENZHONG SHI is the Head and Chair Professor of Geographical Information Science and Remote Sensing in the Department of Land Surveying and Geo-informatics at the Hong Kong Polytechnic University, Hung Hom, Hong Kong, P.R. China. E-mail: [email protected]. His research interests include GIScience and remote sensing, focusing on uncertainties and quality control of spatial data, satellite images and LiDAR data, 3D modeling, and human dynamics.

Anshu Zhang

ANSHU ZHANG is a Postdoctoral Fellow in the Department of Land Surveying and Geo-informatics at the Hong Kong Polytechnic University, Hung Hom, Hong Kong, P.R. China. E-mail: [email protected]. Her research interests include spatial data mining, human dynamics, and machine learning for human geography.

Xiaolin Zhou

XIAOLIN ZHOU is a PhD student in the Department of Land Surveying and Geo-informatics at the Hong Kong Polytechnic University, Hung Hom, Hong Kong, P.R. China. E-mail: [email protected]. Her research interests include GIScience, location-based social networks, and commercial site selection.

Min Zhang

MIN ZHANG is a PhD student in the School of Remote Sensing and Information Engineering at Wuhan University, Wuhan, Hubei, P.R. China. E-mail: [email protected]. His research interests include GIScience, spatial data quality, change detection with satellite images, and deep learning for remote sensing.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 53.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
USD 312.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.