Big Spatial Data covers a wide spectrum of data types including (a) Raster data, e.g. Geoimages, (b) Vector data, e.g., Points, Lines, Polygons, and (c) Graph data, e.g. Road network graph. Thus, “Big Spatial Data” deals with massive amounts of real-time spatial and spatio-temporal data obtained from billions of sensors, location-aware devices, remoting sensing satellites, and various models of the physical world. The use of Big Spatial Data spans a variety of applications including social networks, earth sciences, transportation, communication networks, online maps, smart cities and urban planning, remote sensing, and crisis and evacuation management, to name but a few. Turning Big Spatial Data into value is challenging and requires introduction of fundamentally new spatio-temporal algorithms, methods, and systems that can store, mine, and analyze massive amounts of fast growing and heterogeneous spatio-temporal data in a timely manner.
The aim of this workshop is to bring together researchers and stakeholders from academia, government, and industry who are encountering and actively addressing problems in the area of Big Spatial Data management and analysis. This workshop offers the audience the opportunity to discuss the lessons which they have learned over the years, to demonstrate what they have achieved so far, and to plan for the future of “Big Spatial Data”.




Call for Papers


We encourage researchers from academia and industry to submit papers that highlight the value of Big Spatial Data processing, management, mining, and analysis on topics that include, but are not limited to the following

  • ● Big Spatial Data: Fundamentals and Theory
  • ● Big Spatial Data: Management
  • ● Big Spatial Data: Mining and Analysis
  • ● Big Spatial Data: Stream Processing
  • ● Big Spatial Data: Spatial Time Series Querying and Mining
  • ● Big Spatial Data: Spatial Graph Processing
  • ● Big Spatial Data: Privacy and Authentication
  • ● Big Spatial Data: Descriptive, Predictive, and Prescriptive Models
  • ● Big Spatial Data: Geosensing
  • ● Big Spatial Data: Indexing
  • ● Big Spatial Data: Modern Hardware, High Performance Computing, and Cloud
  • ● Big Spatial Data: Visualization
  • ● Big Spatial Data: Deep Learning
  • ● Big Spatial Data: NoSQL and NewSQL Data Stores
  • ● Big Spatial Data: Data Frameworks
  • ● Big Geospatial Information Retrieval and Crowdsourcing
  • ● Big Geosocial Networks
  • ● Big Spatial Data Applications: Smart Cities and Intelligent Transportation, Urban Computing, Healthcare, Geosciences, etc.



Important Dates


Paper Submission Deadline: October 1, 2021 October 15, 2021 October 18, 2021
Notification of Acceptance: November 1, 2021 November 5, 2021 November 8, 2021
Camera-Ready Submissions: November 15, 2021
Workshop Date: December 15-18, 2021




Submission


Authors with interests in any of the listed topics or any other topic related to Big Spatial Data paradigm are cordially invited to submit their work. All submissions should be in high quality, original and not published or under review elsewhere during the review process.

Submitted papers have to follow the IEEE official template. Maximum paper length allowed is:
● Full Papers: 10 pages
● Short (work-in-progress) Papers: 4 pages
● Demo Papers: 4 pages
● Position/Vision Papers: 4 pages

If from last three categoizes listed above, the title of the paper should start with “Short Paper:”, “Demo Paper:”, or “Vision Paper:”, respectively. Submitted papers will be reviewed by members of the Workshop Program Committee. At least one author for each accepted paper has to register and present the work.
Paper submission website: Submit.




Keynote: Uncertainty Revisited


Abstract: Recent advances in hardware accelerators and computational techniques mean greater opportunity than ever in representing and assessing uncertainty within big spatial data workflows. I take this opportunity to pause and reflect broadly on uncertainty, its origins, representations, and how we can leverage uncertainty quantification in our modeling and in those decision support processes that rely on them. Using a significant and ongoing building occupancy project as motivation, I explore issues of uncertainty emerging from domain expertise, data harmonization, multi-modal integration, and linkages within a machine learning (Bayesian) environment. I revisit mechanisms for acquisition, propagation, conveyance, and understanding of uncertainty both among technical and non-technical consumers of our work. Of particular importance, is careful alignment of language, meaning, and understanding about uncertainty in the final decision making step. I share my own perspectives in communicating uncertainty to decision makers and finish by enumerating some areas I feel are important for further development by our community.


Bio: Dr. Robert Stewart is senior scientist in the GeoAI group at the Oak Ridge National Laboratory (ORNL) engaging in interdisciplinary R&D across several application lanes including population dynamics, sociocultural/economic applications, maritime safety, secure transportation, environmental risk and many others. His own research is focused on statistical and computational methods in the areas of spatio-temporal analytics, probability modeling, and uncertainty quantification with an emphasis on risk and decision support. Research outcomes have led to innovative capability development and deployments including the Spatial Analysis and Decision Assistance (SADA) program, the World Spatio-Temporal Analytics and Mapping Project (WSTAMP), Global Building Intelligence (GBI), Bayesian knowledge models for human dynamics, and GeoAI applications in imagery and non-imagery exploitation. Robert also engages graduate students in geography, mathematics, and the Bredesen Center Data Science Ph.D. regularly serving on thesis committees, advising, and facilitating internships at ORNL.




Program


Start (EST) End (EST) Event
9:00 9:05 Opening Remarks
9:05 10:30 Paper Presentation Session #1
9:05 10:10 Keynote: Uncertainty Revisited
  • ● Dr. Robert Stewart (ORNL)
10:10 10:30 Towards a Model-Driven Datacube Analytics Language
10:30 10:40 Coffee Break
10:40 11:50 Paper Presentation Session #2
10:40 11:00 Fast Gaussian Process Estimation for Large-Scale In Situ Inference using Convolutional Neural Networks
11:00 11:15 Prioritized Sampling on Knowledge Distillation for Nowcasting Pluvial Flood Prediction
11:15 11:30 Development of a Reinforcement Learning based Agent Model and People Flow Data to Mega Metropolitan Area
11:30 11:50 A Holistic Spatial Platform For Managing Infectious Diseases, Case Study on COVID-19 Pandemic
11:50 12:00 Coffee Break
12:00 1:10 Paper Presentation Session #3
12:00 12:20 Containerization of Model Fitting Workloads over Spatial Datasets
12:20 12:35 A Scalable System for Searching Large-scale Multi-sensor Remote Sensing Image Collections
12:35 12:50 Map4OLAP: A web-based tool for interactive map visualization of OLAP queries
12:50 1:10 Decentralized Storage for Scientific Data
1:10 1:15 Closing Remarks



Registration


IEEE BIG DATA 2021




Accommodations


N/A (online conference)




Organizers


Workshop Co-chairs

Farnoush Banaei-Kashani, farnoush.banaei-kashani@ucdenver.edu, University of Colorado Denver

Farnoush Banaei-Kashani is currently an assistant professor at the Department of Computer Science and Engineering, College of Engineering and Applied Science, University of Colorado Denver. Previously, he was a research scientist at the Computer Science Department, University of Southern California (USC), where he also earned his PhD degree in Computer Science and MS degree in Electrical Engineering in 2007 and 2002, respectively. Dr. Banaei-Kashani is passionate about performing fundamental research toward building practical, large-scale data-intensive systems, with particular interest in Data-driven Decision-making Systems (DDSs), i.e., systems that automate the process of decision-making based on (big) data. In the past he has introduced a number of novel DDSs in various application areas (including, transportation, health, safety and security, energy, and scientific computing). Dr. Banaei-Kashani has published more than 65 referred papers and has received several awards. His research has been supported by grants from both governmental agencies (NSF/CENS, NIH/CTSI, DOT/METRANS, DOJ/NIJ and NASA/JPL) and industry (Google, IBM, Chevron and NGC).


Chengyang Zhang, cyzhang@amazon.com, Amazon

Chengyang Zhang is currently a Software Development Manager at Amazon.com leading a team across retail and AWS on PartiQL - A SQL-compatible access to relational, semi-structured, and nested data. He completed his PhD in Computer Science from the University of North Texas in 2011. Dr. Zhang is actively working on various projects related to database and machine learning systems. His research interests includes query processing, spatial databases and bridging database with ML systems. Dr. Zhang has published over 20 peer reviewed papers and owns 5 patents.


Abdeltawab Hendawi, hendawi@uri.edu, University of Rhode Island

Abdeltawab Hendawi is currently an Assistant Professor in the Department of Computer Science and Statistics at the University of Rhode Island, and the Co-director of the AI-Lab at URI. He obtained his MSc and PhD in Computer Science and Engineering from the University of Minnesota, Twin Cities. His research interests are in big data management and analytics with applications in smart city and smart health. Dr. Hendawi has won a number of awards, including the Best Paper Award at the ACM SIGSPATIAL MobiGIS 2012, the Best Design/Plan Poster Award at the U-Spatial Symposium 2013; Best Overall Poster Award, also at the U-Spatial Symposium 2013; the Best Demo Paper Award at the ACM SIGSPATIAL 2014; and Best and Second Best Demo Paper Awards at the IEEE Mobile Data Management (MDM) 2015. My vision for the future research challenges in the area of location-aware services also won a highly recognized Award at the ACM SIGSPATIAL 2016. In addition, he is the recipient of the Hobby Postdoctoral Research Fellowship 2015-2018 from the Computer Science Department at the University of Virginia, and the Best Poster Award at the UVa Research Symposium 2018; and Best Demo Paper Award Runner-up at ACM SIGSPATIAL 2018. He has been a co-chair for the IEEE Big Spatial Data workshop (BSD) 2016 to 2021.


Ashwin Shashidharan , AShashidharan@esri.com, Esri

Ashwin Shashidharan is currently a Software Developer at Esri with the GeoAnalytics team, where he actively works on developing scalable algorithms to analyze large spatiotemporal datasets. He received his MS and PhD degrees in Computer Science from North Carolina State University. His research interests include geospatial simulation, big spatial data management and distributed spatiotemporal analytics. Dr. Shashidharan has won a number of awards, including the Student Research Competition Award at the ACM SIGSPATIAL SRC 2016, and the Esri EDC International Student Award 2018. He has co-authored over 10 peer-reviewed papers, served on multiple review committees (SSTD, SSTDM, ANNSIM, GeoSim and BigSpatial) and has served as co-chair for the ACM SIGSPATIAL BigSpatial workshop (2019-2020).



Program Committee

● Louai Alarabi, Umm Al Qura University, lmarabi@uqu.sa
● Ahmed Eldawy, University of California Riverside, eldawy@ucr.edu
● Xiao Liu, University of Arkansas, xl027@uark.edu
● Amr Magdy, University of California, Riverside, amr@cs.ucr.edu
● Carlo Siebenschuh, IBM, carlo.siebenschuh@ibm.com
● Fusheng Wang, Stony Brook University, fusheng.wang@stonybrook.edu
● Jianting Zhang, City College of New York and CUNY Graduate Center, jzhang1@ccny.cuny.edu
● Demetris Zeinalipour, University of Cyprus, dzeina@cs.ucy.ac.cy


Webmaster

● Shahab Helmi, shahab.helmi@ucdenver.edu
● Amin Pahlavani, amin.pahlavani@ucdenver.edu