Spatial Data Science Symposium 2021

Spatial and Temporal Thinking in Data-Driven Methods
December 13-14, 2021 - Virtual / Online

Motivation

Spatial and temporal thinking is important because everything happens at some places and at some time, and understanding where and when things happen help us analyze how and why they happened or will happen. Spatial data science is concerned with the representation, modeling, and simulation of spatial processes, as well as with the publication, retrieval, reuse, integration, and analysis of spatial data. It generalizes and unifies research from fields such as geographic information science/geoinformatics, geo/spatial statistics, remote sensing, environmental studies, and transportation studies, and fosters applications of methods developed in these fields to other disciplines ranging from social to physical sciences.

Data-driven methods, such as machine learning models, have been attracting attention from the Geoscience community for the past several years. For instance, they have been successfully used to quantify semantics of place types, to classify geo-tagged images, to predict traffic and air quality, to improve resolution of remotely sensed images, and among others so on. In contrast to non-spatial information, geospatial information may be vague, uncertain, heterogeneous, and multimodal; thus spatial and temporal thinking should be included in techniques such as deep neural networks. For example, there are many questions to be explored: Whether a larger amount of data can compensate for the lack of spatial and temporal thinking; how large a role spatial and temporal thinking play in such data-driven methods; how to integrate data-driven methods with theory-driven methods, such as agent-based modelling; how to represent spatial and temporal knowledge to facilitate efficient reasoning; and how to take spatial uncertainty into the model.

With these questions in mind, the Center for Spatial Studies at the University of California, Santa Barbara plans to host the 2nd Spatial Data Science Symposium virtually this year with a focus on “Spatial and Temporal Thinking in Data-Driven Methods.” The symposium aims to bring together researchers from both academia and industry to discuss experiences, insights, methodologies, and applications, taking spatial and temporal knowledge into account while addressing their domain-specific problems. The format of this symposium will be a combination of keynotes, scientific sessions, as well as paper presentations. We welcome submissions for both papers and sessions (see below).

Registration

Free. The registration is now open: click here to register.

Invited Speakers

Interview

Gilberto Camara, Brazil’s National Institute for Space Research

Gilberto-Camara
We will start our symposium with a live/on-stage, interactive interview with Gilberto Camara, including his take on Spatial Data Science, his career lessons learned, and key challenges for the future. Gilberto will also answer questions from the audience.
----------------------------------------------------------------------------------------------------

Keynote: What Text Can Tell Us About Landscape, and What It Can’t (Yet)?

Ross Purves, University of Zurich

Ross-Puerves

Abstract: In this talk I will explore how we can use text to explore ways in which landscapes are perceived and appreciated through language(s). As a starting point I will discuss societal and scientific needs for information about landscape, focussing on geographically inspired research questions. I'll then explore potential data sources, arguing that small sometimes really is beautiful, especially if we wish to annotate and understand data in depth. I'll then discuss methodological approaches to extracting and analysing texts, demonstrating some successes and failures in work done by our group and others. I'll make the claim that existing methods are mostly more than adequate for the questions that we have, and that spatial data science should think harder about questions, and less about methods.

----------------------------------------------------------------------------------------------------

Keynote: Geospatial Big Data Analytics: Opportunities & Challenges in Present & Future Modes of Operation

Roba Abbas, University of Wollongong

Roba-Abbas
----------------------------------------------------------------------------------------------------

Katina Michael, Arizona State University

Katina-Michael
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------

Abstract: Big data and big data analytics have emerged as prevalent topics today in business and academia, promising a wide range of benefits and insights generated through the analysis of vast and varied datasets. The potential to create an enhanced understanding of consumer and corporate opportunities, through the extraction of trends and patterns, results in many business opportunities but also presents numerous challenges. Increased emphasis is now being placed on the use of geospatial datasets extracted from location-based services to supplement big data derived from other sources. Geospatial big data refers to “geo-enriched” data; that is, data that is supplemented with a geographic component, and when contextualised, layered with additional levels of detail, and analysed, provides some form of “location intelligence”. This talk will reflect on the opportunities and challenges of location intelligence, drawing out the ethical considerations relevant to both present and future modes of operation. GIS is no longer simply bounded by satellite and aerial photography geotagged with demographic market data; rather it has become an integral part of Artificial Intelligence and Machine Learning algorithms, resulting in the fusion of human-centered data for the prediction of behavioural patterns and trends through a variety of operational scenarios facilitated by a variety of emerging technologies inclusive of IOT, biometrics, location-enabled apps, and augmented reality.

----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------

Spatial Data Scientist Career Panel Discussion

Song Gao, University of Wisconsin-Madison

Song-Gao
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
Dr. Song Gao is an Assistant Professor in GIScience at the Department of Geography, University of Wisconsin-Madison, where he leads the GeoDS Lab. His main research interests include Geospatial Data Science and GeoAI approaches to Human Mobility and Social Sensing.
----------------------------------------------------------------------------------------------------

Alina Ristea, University College London

Alina
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
Dr. Alina Ristea is an Assistant Professor (Lecturer) at the Department of Security and Crime Science, University College London (UCL). She has a background in geography, cartography and applied geoinformatics. Her main research interests include geographic and temporal analysis and prediction of crime and disorder within urban areas (with a focus on neighbourhoods variation). Additionally, she is working on dynamic spatiotemporal data (e.g. social media) integration in prediction models.
----------------------------------------------------------------------------------------------------

Ana Basiri, University of Glasgow

Ana
Ana Basiri is a Professor in Geospatial Data Science and a UK Research and Innovation Future Leaders Fellow at the University of Glasgow. Ana leads an interdisciplinary team working on developing solutions that consider gaps, unavailability, and biases in data as a useful source of data itself to make inferences about the underlying reasons that caused missingness or biases- and collaborates with world-leading academic and industrial partners, including Google, Ordnance Survey GB, Uber, Alan Turing Institute. Ana is the Editor in Chief of the Journal of Navigation and has received several awards and prizes, including Women Role Model in Science by Alexander Humboldt and European Commission Marie Cucarie Alumni.
----------------------------------------------------------------------------------------------------

Xiaojian Liu, Procter & Gamble

Xiaojian
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
----------------------------------------------------------------------------------------------------
Xiaojian Liu is a junior data scientist in consumer goods industry. His job mainly involves developing machine learning models to support marketing strategies. Before working in the private sector, Xiaojian focused on spatial data science during his graduate studies in GIS.
----------------------------------------------------------------------------------------------------

Session Organizers/Speakers

Proposed Session 1 (Lightning Talks/Discussion/Mapathon): The Future of Global-Scale Spatial Data Collection and Analyses on Urban (in)Accessibility for People with Disabilities

Jon Froehlich, University of Washington

Fabio Miranda, University of Illinois, Chicago

Maryam Hosseini, Rutgers University/New York University

Jon-Froehlich
Fabio-Miranda
Maryam-Hossein
----------------------------------------------------------------------------------------------------

Proposed Session 2 (Tutorial): Spatial Optimization for Planning and Decision-Making

Susan Burtner, University of California, Santa Barbara

Jing Xu, University of California, Santa Barbara

Su-Burtner
Jing-Xu
----------------------------------------------------------------------------------------------------

Proposed Session 3 (Panel Discussion): From Analysis to Action: Engaging through Spatial Data Science Storytelling

Lauren Bennett, Esri

Lauren-Bennett
----------------------------------------------------------------------------------------------------

Proposed Session 4 (Presentation Series): Examining Social Connection and Segregation by Leveraging Emerging Mobility Data

Xiao Li, Texas A&M

Xiao Huang, University of Arkansas

Xiao-Li
Xiao-Huang
----------------------------------------------------------------------------------------------------

Yang Xu, The Hong Kong Polytechnic Universitys

Qunying Huang, University of Wisconsin-Madison

Yang-Xu
Qunying_Huang
----------------------------------------------------------------------------------------------------

Social Event (Mini-Hackathon): BioGeoRef2021 - Georeferencing Biological Locality Descriptions

Azadeh Izadi, Massey University

Kristin Stock, Massey University

Chris Jones, Cardiff University

Azadeh-Izadi
----------------------------------------------------------------------------------------------------
Kristin-Stock
Chris-Jones
----------------------------------------------------------------------------------------------------

Program

Tentative program is shown below (all are in PST Time).

December 13th
Session Time Title Presenter/Organizer
Welcome + Interview with Gilberto Camara
(Chair: Krzysztof Janowicz)
8:00 – 9:00 - Gilberto Camara, Brazil’s National Institute for Space Research
9:00 – 9:15 Break
Paper Session 1: Spatiotemporal Analysis
(Chair: Judith Verstegen)
9:15 – 9:25 Deriving Spatio-Temporal Geographies of Human Mobility from GPS traces Alessia Calafiore, University of Liverpool
9:25 - 9:35 A Prototypical Geospatial Knowledge Graph And Spatio-Temporal Question Answering for Supply Chain Visibility Silvia Dopler, University of Applied Sciences Upper Austria
9:35 - 9:45 A Taxonomic Classification Approach for Global Spatio-temporal Data Robert Stewart, Oak Ridge National Laboratory
9:45 - 10:00 QA
10:00 – 10:15 Break
Proposed Session 1: Lightning Talks/Discussion/Mapathon 10:15 – 11:45 The Future of Global-Scale Spatial Data Collection and Analyses on Urban (in)Accessibility for People with Disabilities Jon Froehlich, University of Washington; Fabio Miranda, University of Illinois, Chicago; Maryam Hosseini, Rutgers University/New York University
11:45 – 13:00 Break
Paper Session 2: Geospatial Insights
(Chair: Rui Zhu)
13:00 – 13:10 Spatial Linked Data Approach for Trace Data in Digital Humanities Franziska Hübl, Graz University of Technology
13:10 - 13:20 Hidden Spatial Clusters - And How to Find Them? Peter Ranacher, University of Zurich
13:20 - 13:30 Data Augmentation for Spatial Disease Mapping Raphaella Diniz, Simon Fraser University
13:30 - 13:45 QA
13:45 – 14:00 Break
Keynote
(Chair: Grant McKenzie)
14:00 – 15:00 Geospatial Big Data Analytics: Opportunities & Challenges in Present & Future Modes of Operation Roba Abbas, University of Wollongon; Katina Michael, Arizona State University
15:00 – 15:15 Break
Proposed Session 2: Tutorial 15:15 – 16:45 Spatial Optimization for Planning and Decision-Making Susan Burtner, University of California, Santa Barbara; Jiwon Baik, University of California, Santa Barbara; Seonga Cho, University of California, Santa Barbara; Vanessa Echeverri Figueroa, University of California, Santa Barbara; Evgeny Noi, University of California, Santa Barbara; B. Amelia Pludow, University of California, Santa Barbara; Enbo Zhou, University of California, Santa Barbara
16:45 – 17:00 Break
Proposed Social Event: Mini-Hackathon 17:00 – 18:30 BioGeoRef2021 - Georeferencing Biological Locality Descriptions Azadeh Izadi, Massey University; Kristin Stock, Massey University; Chris Jones, Cardiff University; Aaron Wilton, Landcare Research
December 14th
Session Time Title Presenter/Organizer
Paper Session 3: Machine Learning
(Chair: Clio Andris)
8:15 – 8:25 Parking Recommendation Service Using Deep Learning Abouzar Ramezani, Sayyed Jamaleddin Asadabadi University
8:25 - 8:35 am Sidewalk Measurements from Satellite Images: Preliminary Findings Maryam Hosseini, New York University
8:35 - 8:45 Classifying Narcotrafficking Spatial Event Documents using Transformers Morteza Karimzadeh, University of Colorado Boulder
8:45 - 9:00 QA
9:00 – 9:15 Break
Spatial Data Scientist Career Panel Discussion
(Chair: Ourania Kounadi)
9:15 – 10:15 Spatial Data Scientist Career Panel Discussion Song Gao, University of Wisconsin-Madison; Alina Ristea, University College London; Ana Basiri, University of Glasgow; Xiaojian Liu, Procter & Gamble
10:15 – 10:30 Break
Proposed Session 3: Panel Discussion 10:30 – 11:45 From Analysis to Action: Engaging through Spatial Data Science Storytelling Lauren Bennett, Esri; Francesca Dominici, Harvard T.H. Chan School of Public Health; Song Gao, University of Wisconsin-Madison; Kevin Butler, Esri
11:45 – 13:00 Break
Keynote
(Chair: Bruno Martins)
13:00 – 14:00 What Text Can Tell Us About Landscape, And What It Can't (Yet)? Ross Purves, University of Zurich
14:00 – 14:15 Break
Paper Session 4: Geo-Privacy and Geo-Ethics
(Chair: Ling Cai)
14:15 – 14:25 "Data Horror": Mapping (Spatial) Data Privacy Violations onto a Cognitive Account of Horror Daniel Romm, McGill University
14:25 - 14:35 Visualizing Environmental Justice Issues in Urban Areas with A Community Input Approach Joel Flax-Hatch, University of Illinois at Chicago
14:35 - 14:45 A Vision for Veridical Spatial Data Science Peter Kedron, Arizona State University
14:45 - 15:00 QA
15:00 – 15:15 Break
Proposed Session 4: Presentation Series 15:15 – 16:45 Examining Social Connection and Segregation by Leveraging Emerging Mobility Data Xiao Li, Texas A&M; Xiao Huang, University of Arkansas; Yang Xu, The Hong Kong Polytechnic University; Qunying Huang, University of Wisconsin-Madison
Closing Remark 16:45 – 17:00

Call for Papers

We welcome short papers (6 pages) and vision papers (4 pages) on the following (or similar) topics:

  • Spatial and temporal knowledge representation and reasoning
  • Geospatial semantics
  • Geospatial artificial intelligence (GeoAI) & spatially-explicit machine learning
  • Neuro-symbolic representation learning for spatial and temporal data
  • Geographic information retrieval
  • Geospatial knowledge graphs
  • Spatial statistics / Geostatistics
  • Spatial and temporal data mining
  • Spatial and spatiotemporal data uncertainty
  • Geo-simulation
  • Geospatial applications that use data-driven methods, including but not limited to:
    • Movement analysis
    • Disaster response
    • Environmental studies
    • Geoprivacy
    • Social sensing
    • Location-based services
    • Humanitarian relief
    • Crime analysis
    • Urban analytics

Submission Guidelines

We welcome short papers (6 pages) and vision papers (4 pages). All submissions must be original and must not be simultaneously submitted to another journal or conference/workshop. All submissions must be in English. Proceedings of the symposium will be publicly available at well-established UC eScholarship and each accepted paper will be assigned an individual DOI. All papers must be formatted according to LNCS templates. Submissions will be peer-reviewed by the Program Committee. Papers must be submitted via EasyChair: Easychair Sumbmission System.

Several journals have been contacted about the possibility of organizing a special issue following this event. Selected papers will be invited to submit an extended version to the journal. More details will be announced soon.

Call for Session Proposals

We solicit anyone and any team who is interested in Spatial Data Science to propose a session for SDSS 2021. Any activity that can fit into a 90-minute time slot is welcome (longer sessions may be proposed as a combination of multiple slots).

Examples of session type include:
  • a panel discussion
  • a series of presentations on a topic
  • a breakout-style discussion
  • a tutorial
  • hackathon
  • challenges (bring your own “sharks”)
  • education track
  • technology track

Submission Guidelines

In a maximal 2-page submission, please indicate:

  • Name of the session
  • Type of session: Panel / Presentations / Break-out discussion / Tutorial / Education Track / Technology Track / Hackathon / Challenge / Other (please specify)
  • Short description of the session
  • Names and affiliations of team members that will lead the session (preferably 2-3 people)
  • Speakers (when applicable). It is imperative to specify the confirmed speakers if you are proposing a panel
  • Expected participation (i.e., who would be interested in attending your session)
  • Email the proposal directly to Dr. Rui Zhu: ruizhu@geog.ucsb.edu
----------------------------------------------------------------------------------------------------

Important Dates

  • Symposium date: December 13–14, 2021
  • Paper submission deadline: October 30, 2021 November 3, 2021 (extended)
  • Notification of paper acceptance: November 21, 2021 November 24, 2021 (extended)
  • Camera ready version: November 30, 2021 December 3, 2021 (extended)
  • Proposal submission deadline: November 15 2021
  • Notification of session acceptance: November 20 2021
----------------------------------------------------------------------------------------------------

Organizing Committee

General Chair

Program Chairs

  • Rui Zhu, Center for Spatial Studies, University of California Santa Barbara
  • Judith Verstegen, Laboratory of Geo-information Science and Remote Sensing, Wageningen University and Research
  • Ling Cai, Center for Spatial Studies, University of California Santa Barbara
  • Grant McKenzie, Department of Geography, McGill University
  • Ourania Kounadi, Department of Geography, University of Vienna
  • Bruno Martins, Instituto Superior Técnico, University of Lisbon

Local/Virtual Arrangements

  • Karen Doehner, Center for Spatial Studies, University of California Santa Barbara
  • Kitty Currier, Center for Spatial Studies, University of California Santa Barbara

Program Committee

  • Clio Andris, Georgia Tech University
  • Geoff Boeing, University of Southern California
  • Karl Grossner, University of Pittsburgh
  • Yingjie Hu, University at Buffalo
  • Stefan Keller, Eastern Switzerland University of Applied Sciences
  • Wenwen Li, Arizona State University
  • Gengchen Mai, Stanford University
  • Nick Malleson, University of Leeds
  • Trisalyn Nelson, University of California Santa Barbara
  • Ross Purves, University of Zurich
  • Alina Ristea, University College London
  • Colin Robertson, Wilfrid Laurier University
  • Francisco Rowe, University of Liverpool
  • Johannes Scholz, Graz University of Technology
  • Robert Stewart, Oak Ridge National Laboratory
  • Kristin Stock, Massey University
  • Robert Weibel, University of Zurich
  • Feng Zhang, Zhejiang University
  • Bo Zhao, University of Washington
  • Yunqiang Zhu, Chinese Academy of Sciences
  • Alexander Zipf, Heidelberg University

Contact

For any further information, please contact Rui Zhu or Ling Cai.