Current Projects

Comparison of landscapes and spatial patterns in the age of big data

This project aims to develop new methods for comparing spatial patterns derived from spatial models. A key task in handling geographic information is the ability to make inferences about spatial patterns, and increasingly, to compare spatial patterns. This might be in evaluating the fit of a spatially explicit model about the spread of an invasive species, or evaluating whether a landscape has lost significant connectivity after resource extraction has occured. While methods for detecting patterns in spatial data have blossomed, there are decidedly few tools available for comparing spatial patterns about the environment. Given the vast landscape of geographical information sources, there is a growing need for pattern comparison algorithms

Barren-ground caribou population health in relation to a changing winter environment in Northwest Territories

Working with collaborators in the Government of the Northwest Territories and Dr. Michael English we are investigating large-scale patterns in space-time change in winter environmental attributes in winter ranges of barren ground caribou. Determinants of population health being investigated include changes in snowpack structure and seasonality, temperature fluctuations, and habitat quality.

Wildlife health surveillance in Canada

Tracking patterns of widlife health and disease over large areas is extremely difficult. We are working with the Canadian Wildlife Health Cooperative to develop tools and models to better understand changes in wildlife health, focusing on environmental change indicators, web-surveillance, and traditional disease surveillance data as sources for integrated environmental health assessment.

Completed Projects

Integrating social media, geospatial information, and sentiment analysis for the analysis of urban environments

In this project, we will mine social media streams using natural language processing methods, and recontextualize social media expressions through spatial modelling and integration with contextual geospatial datasets describing participants’ immediate surroundings. The study is a partnership development project between Dr. Robertson and researchers from WLU, UW, Loughborough University (UK), University of Ottawa (UoO) and Malatest and Associates Ltd.

Ambient Geospatial Information and Maritime Surveillance

Maritime surveillance encompasses the understanding of all maritime activities that could impact the security, safety, economy or environment of people, places, and the marine environment. Increasingly, automated ship-location data are used as a key source of information in detecting malignant maritime events. In this project are building upon a recently prototyped system for maritime surveillance which integrates open data sources and ambient geospatial information sources to build enhanced contextual knowledge and support more accurate detection of anomalies.

Quality, Uncertainty and Volunteered Geographic Information

The explosion in the production of digital data has created new opportunities to investigate and understand social and natural processes. Geographic data has also seen explosive increase in production through the use of web collaboration, ubiquitous location sensors, and mobile computing. Before widespread adoption of these data sources can be used for research, more understanding of issues of data quality and uncertainty are needed. This research explores different aspects of data quality as it relates to VGI in order to facilitate its application in social and environmental research.

Space-time Modelling of Leptospirosis in Sri Lanka

In collaboration with the Ministry of LIvestock and Rural Community Development, the Department of Meteorology, Sri Lanka, and the Epidemiological Unit, Sri Lanka.

Leptospirosis is one of the most widespread zoonoses in the world. Like many zoonoses, social and environmental processes (rainfall, paddy farming, disease control programming etc) contribute to the spatial and temporal distribution of cases. This research takes a risk-modelling approach to analysis of suspected Leptospirosis cases in Sri Lanka with an aim towards developing early warning models for surveillance.

Spatial Risk Modelling of Japanese Encephalitis in Nepal


Funded by IDRC, in collaboration with the Centre for Coastal Health and the National Zoonoses and Food Hygiene Research Centre, Nepal

Japanese Encephalitis (JE) is a vector-borne zoonotic disease. In Nepal, the geographic distribution of cases has been changing in recent years, to higher elevations and urban and peri-urban locations. This project examines the spatial distribution of risk and risk factors for JE occurring coincident changes in its epidemiology.