August 1 The Early Career Panel has been announced.
June 26 Registration is now open and the symposium schedule is online: Schedule/Program
May 17 The paper submission deadline has been extended to May 29th.
May 3 The thematic sessions have been announced.
May 1 The SDSS2023 keynote speakers have been announced.
Apr 25 This year's interviewees have been announced.
Spatial and temporal thinking is important not just because everything happens at some places and at some time, but because knowing where and when things are happening is key to understanding 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 such space- and place-centric 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 in other disciplines ranging from social to biological and 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 the semantics of place types, to classify geo-tagged images, to predict traffic and air quality, to improve resolution of remotely sensed images, to recognize objects in such imagery, to predict and compare trajectories, to name but a few. Geospatial observations may be vague, uncertain, heterogeneous, dependent on other nearby observations, biased, and multimodal; thus, spatial and temporal principles should be included in data science techniques such as deep neural networks. Unsurprisingly, research has shown that by doing so, we can substantially outcompete more general (non-spatial) models when applied to geo-data or applications with a spatial and temporal component.
To keep this discussion alive and help the community to exchange ideas and lessons learned about spatial and temporal aspects of data science, we are hosting the 4th Spatial Data Science Symposium (SDSS 2023) as a distributed virtual meeting. 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. In contrast to classical conferences, the community will decide on those sessions, and the main focus will be on interaction. Hence, we welcome submissions for both papers and sessions (see below). SDSS 2023 will be a distributed symposium in a sense that while the event as such will be online, we will host (and help others to host) individual get-togethers to jointly experience the symposium in person.
Paper submission deadline: May 22, 2023 May 29, 2023
Session submission deadline: April 14, 2023 April 21, 2023
Paper notification: July 10, 2023
Symposium Dates: September 5-6, 2023
We welcome short papers (3,000 words) and vision papers (2,000 words) on the following (or similar) topics:
All submissions must be original and must not be simultaneously submitted to another journal or conference/workshop. All submissions must be in English and formatted according to LNCS templates. Proceedings of the symposium will be publicly available at well-established UC eScholarship and each accepted paper will be assigned an individual DOI. Submissions will be peer-reviewed by the Program Committee. Papers must be submitted via EasyChair.
This year we are happy to welcome two keynote speakers who are working on the cutting edge of spatial data science.
Abstract
Finding optimal plans of action becomes more critical as space (e.g. in land use) and time (e.g. in climate change) become more scarce. At the same time, we're aware that in most, if not all, cases, there is no such thing as an optimal plan, as complex problems have multiple stakeholders with multiple conflicting objectives, e.g., preserving biodiversity and increasing food production. That means that trade-offs exist between these objectives. Geoscientists traditionally use simulation models with different scenarios, e.g. a 'nature preservation' scenario versus an 'economic development' scenario to show trade-offs. However, this gives only two points in the entire solution space of action plans and their corresponding spatial arrangements. Spatial optimization methods can contribute to debates by showing the whole Pareto front, i.e. all optimal spatial arrangements given all conflicting objectives. In this talk, I will substantiate this argument, but also point at the geocomputational challenges ahead.
Biography
I am an Assistant Professor at the Department of Human Geography and Spatial Planning, Utrecht University, The Netherlands. My research is focused on two sets of methods in Geo-Information Science: geosimulation modelling and spatial optimization. I like working with domain experts to apply these methods to their system of interest, because it allows me to meet interesting people and see the world from different viewpoints.
Abstract
The ubiquity of gadgets and smart things, such as mobile phones and smartwatches, has given us an unprecedented opportunity to zoom into individuals but still see the bigger picture of cities and society almost in real time for free. However, such "new forms of data” are incomplete, sparse, biased, and under-represented. This talk will look at the quality-quantity tradeoff of big geospatial data and the challenges, theoretical and applied solutions to effectively combine and make the most of both the traditional and new forms of data, and use missing data as useful data to understand why and how missingness happens in the first place.
Biography
Ana Basiri is a Professor in Geospatial Data Science, a UK Research and Innovation Future Leaders Fellow, the Director of Centre for Data Science and AI, and Royal Academy of Engineering's EngineeringX Champion at the University of Glasgow. Ana works on developing (theoretical and applied) solutions that consider unavailability and biases in data as useful source of data to make inferences about the underlying reasons that caused missingness or biases. Her research is funded by UK Research and Innovation, European Research Council, and Royal Society, RAEng, and Alan Turing Institute allowing her to build and lead a team of an interdisciplinary team and collaborate with world-leading academic and industrial partners, including Uber, and Google. 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 Curie Alumni.
The symposium will feature a live/on-stage, interactive interview with Anna Lopez-Carr and Andrew Schroeder from Direct Relief, including their insights into how they make use of Spatial Data Science methods for humanitarian relief, how they use or plan to use GeoAI and knowledge graphs, and key challenges for the future of increasingly data and AI/ML-heavy decision-making in times of crisis. Anna and Andrew will also answer questions from the audience.
Direct Relief
Direct Relief
Along with regular paper presentations, this year's symposium will feature seven thematic sessions organized by a variety of teams from around the globe. The session titles and organizers are listed below. More details will be added as they become available.
In this workshop, we will present 1) working prototypes of infrastructure to facilitate reproducibility and open science, 2) exemplar cases of reproduction and replication studies in spatial data science, and 3) a reproducibility and replicability curriculum. We have developed this framework of infrastructure, cases and curriculum over the course of a three-year National Science Foundation award, Transforming theory-building and STEM education through reproductions and replications in the geographical sciences. Following presentations, we will form breakout groups to discuss applications to individual research programs and future steps for scaling up reproducible research practices in spatial data science.
Further Details
n cutting-edge spatial learning methods, the 'neighborhood' is often used as a way to pool information, improving predictions and regularising estimates. But, the correspondence between the statistically-useful neighborhoods that our methods identify and the actual neighborhoods that matter to people is generally unknown and under-examined. Instead, new methods proceed apace, coming up with new, better, more efficient ways of learning from context. This session seeks to provide a platform for those interested in neighborhood effects themselves and their correspondence with the neighborhoods that are salient for individual behavior. In addition, this session seeks to provide a home for those interested in developing new local spatial learning methods that learn from geographical context to improve predictions or regularise estimates.
Further Details
Urban and wellbeing analytics are fields that aim to support assessments, projections, and interventions that determine the economic and social wellbeing of people, businesses, governments, and third sector agencies in urban environments. Both fields draw heavily from geospatial data collected by conventional methods such as censuses and surveys, in conjunction with novel datatypes provided by the increasingly widespread urban network of location enabled devices. This presentation series aims to address the recent trends in urban and wellbeing analytics that are shaping the information available to evidence-based policy making in areas, including but not limited to, health, transportation, policing, disaster response and risk management.
Further Details
Join us at SDSS for our enlightening session, "Street view imagery: Have we answered all the questions with it? What's left to do?". Hosted by Koichi Ito and Winston Yap from the Urban Analytics Lab, National University of Singapore, this session is a blend of insightful presentations and enlightening Q&A segments. The session will explore the undiscovered potential of Street View Imagery (SVI) and foster open discussions on innovative research topics and future challenges. Our speakers, experts in SVI, will share their knowledge, encouraging both new and experienced researchers to delve deeper into the field.
Further Details
Natural disasters, such as hurricanes, floods, tornados, wildfires, earthquakes, and blizzards, pose significant threats to people and society. The availability of various geospatial data sources (e.g., drone-collected images, mobile phone location data, social media data, and sensor network data) combined with the advancement of statistical and machine learning models provide great opportunities for understanding human-environment interactions during these catastrophic events. This session aims to bring together researchers interested in using spatial data science to answer questions and address issues in any aspect related to disaster management.
Further Details
As in previous years, this iteration of the Spatial Data Science symposium will feature a panel of early career researchers. Panelists will share their experiences as spatial data scientists and discuss challenges and opportunities facing researchers in the early stages of their careers.
Te Manatū Waka, Ministry of Transport, New Zealand
School of Geography and Sustainable Development at The University of St Andrews, UK
University of Canterbury, Christchurch, New Zealand
University of Canterbury, Christchurch, New Zealand
UC Santa Barbara
Austrian Institute of Technology
University at Buffalo
McGill University
ETH Zurich
University of Bristol
University of Vienna & Spatial Center,
UC Santa Barbara
SDSS2023 is a distributed/online symposium. Participants are welcome to join one of the symposium hubs distributed around the world. Groups of participants will meet at these hubs to present and discuss with other participants both in person and online.
If you are interested in hosting a hub in your city, please contact grant.mckenzie@mcgill.ca.
Contact: grant.mckenzie@mcgill.ca
Contact: vanessa.bastos@canterbury.ac.nz
Contact: victoria.fast@ucalgary.ca
Contact: yhu42@buffalo.edu
Contact: rui.zhu@bristol.ac.uk
Contact: nwiedemann@ethz.ch
Contact: minh.kieu@auckland.ac.nz
Contact: j.a.verstegen@uu.nl
Contact: toshan@umd.edu