NSF Workshop on Geospatial Data Science in the Era of Big Data and CyberGIS

Sponsored by the National Science Foundation (NSF)
Urbana, Illinois, USA
July 25-26, 2016

The complexity, diversity, and rapid growth of geospatial data have increased significantly over recent decades and are driving discoveries in a large number of application and science domains. Access to and interaction with geospatial big data collected from numerous sources are increasingly fundamental to explore natural, human and social systems at unprecedented scales and provide tremendous opportunities to gain dynamic insight into complex phenomena through big compute (e.g. cloud and high-performance computing) and cyberGIS approaches. CyberGIS (geographic information science and systems (GIS) based on advanced cyberinfrastructure) represents new-generation GIS in the era of big data and has emerged during the past several years as a vibrant interdisciplinary field. Though geospatial big data have played important roles in many domains and promise to enable a wide range of decision-making practices with significant societal impacts, geospatial data science remains to be established for advancing leading-edge research and education in the era of big data and cyberGIS.

The primary goal of this workshop is to bring together thought leaders and cutting-edge researchers from pertinent multidisciplinary communities to explore the frontiers of geospatial data science. Specifically, the two-day workshop aims to:

  • Introduce geospatial big data capabilities (e.g., LiDAR, remote sensing, and location-based social media) for novel applications (e.g., urban sustainability and interdisciplinary studies);
  • Demonstrate cutting-edge cloud computing and cyberGIS tools for scalable spatial data synthesis and enhancing knowledge discovery power based on geospatial big data;
  • Identify spatial data synthesis requirements from representative science drivers;
  • Formulate a core set of questions and problems of geospatial data science; and
  • Discuss foundations and principles of geospatial data science.

Workshop Themes

  • Domain science drivers and questions
  • Fundamentals and principles
  • Methods and theories
  • Analysis and synthesis
  • Capabilities and tools



7:30 AM – Breakfast
8:00 AM – Welcome and Introduction – Shaowen Wang
8:10 AM – Shaowen Wang – CyberGIS and Geospatial Data Science — Chair: Kate Keahey
8:30 AM – Keynote: Ed Seidel, National Center for Supercomputing Applications (NCSA), University of Illinois at Urbana-Champaign (UIUC) — Chair: Shaowen Wang

  • Big Data Science and National Data Service

9:15 AM – Lightning Talks on Domain Science Drivers and Questions — Chair: Anand Padmanabhan

  • Kaiyu Guan, Jian Peng, Shaowen Wang & Yaping Cai: Forecasting crop types for the US Corn Belt using fused satellite images
  • Xingong Li: Modeling Solar Radiation Through Cloud Computing
  • Timothy Nyerges, Keith Reynolds & Philip Murphy: Big Data for Complex Sustainable Systems Models in Decision Support
  • George Percivall. Big Geospatial Data: An Open Approach to Loosely-Coupled Ecosystems
  • Britta Ricker: CyberGIS to Facilitate Unmanned Aerial Systems Volunteered Big Raster Data
  • William Stewart, Andrew Greenlee, Paul Gobster, & Carena van Riper: Spatial Contagion of Urban Greening: Exploring a CyberGIS Approach
  • Jin Xing & Renee Sieber: Geospatial CyberInfrastructure in Land Use/Cover Change Research

10:30 AM – Break
10:45 AM – Breakout Discussions — Introduced by Shaowen Wang

  • Group 1: Domain Science Drivers and Questions — Chair: Witold F. Krajewski
  • Group 2: Capabilities and Tools — Chair: Paul Ruth
  • Group 3: Grand Challenges in Geospatial Data Science — Chair: Michael Bishop

11:45 PM – Report Back
12:00 PM – Brown Bag Talk: Arfon Smith, Github — Chair: Daniel S. Katz

  • Making Science More Open

1:20 PM – Invited Talk: Kate Keahey, Argonne National Lab / University of Chicago — Chair: Shaowen Wang

  • Cloud Innovation for Scalable Geospatial Data Science

1:40 PM – Lightning Talks on Capabilities and Tools — Chair: Kate Keahey

  • William Catino, Managing Sensor-based Data Streams with Waggle
  • David Haynes & Steven Manson: Advanced CyberInfrastructure for Analysis of Big Spatial Data
  • Andrew Johnson, Arthur Nishimoto, Alessandro Febretti & Jillian Aurisano: Immersive Geospatial Analytics
  • Sushil Prasad, Danial Aghajarian & Satish Puri: A High Performance Spatial Join on GPU & Parallel I/O for Vector Data
  • Judy Qui. High Performance Analytics Libraries for Spatial Big Data using Harp
  • Paul Ruth: Advanced Cloud Networking for Science Applications
  • Ranga Raju Vatsavai: Remote Sensing Big Data Mining Framework for Monitoring Global Resources

2:45 PM – Break
3:15PM – Demos of CyberGIS and Geospatial Big Data Examples — Chair: Anand Padmanabhan
4:00 PM – Breakout Discussions

  • Group 1: Fundamentals and Principles — Chair: Timothy Nyerges
  • Group 2: Methods and Theories — Chair: Ranga Raju Vatsavai
  • Group 3: Education and Workforce — Chair: Britta Ricker

5:00 PM – Report Back
5:30 PM – Break
6:00 PM – Dinner Keynote Speaker: Victoria Stodden, UIUC — Chair: Shaowen Wang

  • Reproducibility in Geospatial Sciences and Technologies

7:30 PM – Adjourn the Program on Monday


7:30 AM – Breakfast
8:00 AM – Welcome – Shaowen Wang
8:15 AM – Keynote: Witold F. Krajewski, the University of Iowa — Chair: Kate Keahey

  • Environmental Prediction Everywhere: Coming Soon to a Theater Near You

9:00 AM – Lightning Talks on Fundamentals and Principles — Chair: Anand Padmanabhan

  • Michael Bishop: Scientific Foundations for Geospatial Big Data & CyberGIS in the Geosciences
  • Matthew Haffner & Adam Mathews: A Multi-Dimensional Topology for Crowdsourced Geographic Information
  • David Kimmey & Jin Soung Yoo: Nowcasting with Location-based Social Media
  • Bo Li: Drawing Statistical Inferences for Spatial and Spatio-temporal Data
  • Kytt MacManus: Bad Data Leads to Bad Decisions
  • Samuel Stehle: Who Evaluates the Evaluator? Reconsidering Validation of Classification Processes Under Big Data

10:15 AM – Break
10:30 AM – Panel (Panelists: Michael Bishop, Charlie Catlett, George Percivall, Judy Qiu, Keith M. Reynolds, Paul Ruth, & Victoria Stodden) Discussion on the Following Questions — Chair: Shaowen Wang

  • What should we have addressed that we did not?
  • What are the most significant things learned?
  • What should be done next informed from the workshop?

12:00 PM – Lunch
1:00 PM – Adjourn the Workshop

Workshop Materials

See this Google Drive folder

Position Papers

You can find it in this Google Drive folder.

Workshop Chairs

  • Shaowen Wang, CyberGIS Center, National Center for Supercomputing Applications (NCSA), UIUC; University Consortium for Geographic Information Science (UCGIS)
  • Kate Keahey, Argonne National Lab and University of Chicago
  • Anand Padmanabhan, CyberGIS Center, NCSA, UIUC


The workshop will be held at the National Center for Supercomputing Applications, 1205 W. Clark St., Urbana, IL 61801.

Workshop Hotel

A block of rooms has been reserved at the Hampton Inn, across the street from NCSA. See the reservation information on the CyberGIS’16 pageThe registration deadline is Friday, July 15th


Please contact gds16@cybergis.org