Workshops and Tutorials

This year, we had a total of 27 submissions for pre-conference workshops and tutorials! Below are a list of accepted workshops and tutorials for GIScience 2016. All workshops (WK) and tutorials (T) are held on September 27th, 2016, the day before the start of the conference (schedule). Remember that you must register for the conference to be able to register for the pre-conference workshops.

Workshops

Understanding Spatial Data (Big and Small) with Visual Analytics

Format: Full day

OrganizersUrska Demsar and Anthony Robinson

Website

The workshop calls for new visual analytics methods and applications for spatial or spatio-temporal data, which demonstrate the usefulness of these techniques for analytical reasoning about space and time. We are particularly interested in how the inclusion of the interactive visualisations into the analysis adds to the understanding of spatial data, either big or small. We call for submissions in any application area using any data type. We further encourage approaches that take advantage of both spatial and temporal characteristics of such data, those that allow analysis across different spatial or temporal scales and those that provide new dynamic interactive visualisations for data exploration. This is a full-day workshop with keynote addresses and a programme of peer-reviewed contributions.

Analysis of Movement Data 2016

Format: Full day

OrganizersSomaya DodgePatrick Laube, Jed LongRobert Weibel

Website

The past 10-15 years have seen a dramatic improvement of positioning technologies, which led to massive volumes of tracking data about virtually any object that moves, in a multitude of application domains. Consequently, many new methods for these data have been developed, and computational movement analysis has evolved as an important stream of research in GIScience. However, many challenges remain, such as integration of trajectories with space-time environmental data, multi-sensor data integration, scale-adaptive analysis, integration of analytical and visual methods, modeling and simulation of movement, passing from individual to collective movement, or linking patterns back to behavioural events and processes.

This workshop pursues two objectives. First, to provide a platform to discuss recent trends, and review the current state of the art in this domain. And second, to identify the key challenges for future research and (re-)define the research agenda. These objectives will be pursued using a mix of short presentations, a panel discussion, and break-out and plenary sessions.

Spatial Data on the Web (SDW16)

Format: Full day

OrganizersKrzysztof Janowicz

Website

In their first joint collaboration, the OGC and W3C have established the Spatial Data on the Web Working Group. The group aims at investigating and providing guidance for the following challenges: (1) how can spatial information best be integrated with other data on the Web; (2) how can machines and people discover that different facts in different datasets relate to the same place; (3) and what are existing methods/tools to publish, discover, reuse, and integrate spatial data. The GIScience community has a long standing interest and expertise in many of these issues. Therefore, this workshop aims at bringing researchers together to (1) discuss challenges in publishing spatial data on the Web, (2) identify best practices, (3) point out theoretical foundations that need strengthening, (4) identify common quality issues, (5) improve/develop existing ontologies for the semantic annotation of spatial data, and (6) discuss interface and services that will further improve data linking, sharing, and retrieval across communities.

Geosocial: Social Media and GIScience

Format: Full day

OrganizersTony StefanidisDaniel SuiMing-Hisang Tsou

Website

This day-long workshop aims to serve as a platform to discuss and showcase the complex issues associated with the analysis of social media contributions in the context of GIScience. Spanning spatial footprints, social networks, and sociocultural themes, such data can support a variety of applications, ranging from disaster response and environmental monitoring to health informatics and digital citizenship. Given their variations in accuracy, the complex patterns of participation, and the constantly increasing data volumes, analyzing such data in a meaningful, reliable, and timely manner is a substantial challenge. The objective of this workshop is to showcase on-going research in the GIScience community on the analysis of social media content and thus support the emergence of a cohesive research agenda in our community.

Rethinking the ABCs: Agent-Based Models and Complexity Science in the age of Big Data, CyberGIS, and Sensor Networks

Format: Full day

OrganizersRaja SenguptaEun-Kyeong KimLiliana PerezDaniel G. Brown

Website

A broad scope of concepts and methodologies from complexity science – including Agent-Based Models, Cellular Automata, network theory, and scaling relations – has contributed to a better understanding of spatial/temporal dynamics of complex geographic patterns and process.

Recent advances in computational technologies such as Big Data, Cloud Computing and CyberGIS platforms, and Sensor Networks (i.e. the Internet of Things) provides both new opportunities and raises new challenges for ABM and complexity theory research within GIScience.  Challenges include parameterization of complex models with volumes of georeferenced data, scaling model applications to realistic, exploring challenges in their deployment across cloud computing platforms, and validating their output using real-time data; as well as measure the impact of simulation on knowledge, information and decision-making.

The scope of this workshop is to explore novel complexity science approaches to dynamic geographic phenomena and their applications, addressing challenges and enriching research methodologies in geography in a Big Data Era.

Tutorials

Machine learning methods for spatial and temporal analysis

Format: Full day

OrganizersJames Haworth

Website

Machine learning (ML) methods have gained popularity in the GIScience community over the past few decades due to their success in dealing with the nonlinearities and heterogeneities of spatial and temporal datasets. However, their uptake is somewhat limited due to the steep learning curve. This workshop aims to provide a gentle, practical introduction to ML methods for addressing two common problems in spatial and temporal analysis: classification and regression. Attendees will be taught the key concepts underpinning a range of ML algorithms, including support vector machines and random forests. They will then be taught the essential skills necessary to train and test ML models using R statistical package. A number of real world datasets will be used as examples, including GPS tracks, road traffic data and environmental data. The workshop will conclude with a discussion of some the limitations of ML methods, advanced topics and future research directions.