The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Geographic Information Science

Geographic Information Science (GIS) is a field that studies how to collect, analyze, visualize, and understand location-based data. It helps people recognize patterns in geography and make informed decisions in different areas.

Our department explores GIS from many angles, including traditional spatial analysis, advanced geospatial methods, and diverse GIS applications.

Traditional Spatial Analysis

Traditional spatial analysis focuses on methods used to study how things are distributed and connected across space. These methods include:

  • Spatial statistics: Using mathematical calculations to study geographic patterns.
  • Spatial interpolation: Estimating missing data points based on nearby values.
  • Network analysis: Examining connections between locations, such as road networks.
  • Geostatistics: Understanding spatial dependencies in natural environments.

Common techniques such as spatial autocorrelation (studying how nearby locations affect each other), nearest neighbor analysis (examining how close objects are), and kernel density estimation (mapping concentrations of data) are applied in areas like urban planning and environmental studies.

Advanced Geospatial Methods

Our research in advanced geospatial methods uses modern technologies and innovative approaches to solve complex spatial challenges.

  • Geospatial Artificial Intelligence (GeoAI): We combine machine learning, Generative AI, and Large Language Models (LLMs) with spatial data science to improve pattern recognition, predictive modeling, and automated geospatial analysis.
  • 3D Modeling and Digital Twins: These technologies allow us to create detailed three-dimensional models of real-world environments. They help in areas such as smart cities, urban planning, infrastructure management, and environmental monitoring.
  • Spatial Data Infrastructures (SDI): Our research focuses on building and improving frameworks for collecting, sharing, and managing spatial data. We emphasize technical aspects such as geospatial web services, linked geo-data, and the semantic web to improve data integration and accessibility.
  • Spatial Multicriteria Decision Analysis (MCDA): MCDA is a method used to analyze complex decisions by considering multiple conflicting factors at once. It helps in spatial problem solving by balancing different criteria, weighting their importance, and incorporating stakeholder preferences to find the best solutions. We use both multi-
  • attribute and multi-objective optimization techniques to support better decision-making in spatial analysis.
  • Algorithm and Model Development: We develop and improve algorithms and models to efficiently process high-resolution spatial data collected over time.
  • Cartography: We create new techniques to improve how geospatial data is visualized, making maps and spatial representations clearer and more informative.

GIS Applications

GIS applications at the core of our research and play a crucial role in solving real-world challenges across different fields. Our research applies GIS techniques to various important applications, including:

  • Climate, environment, and ecosystem: Investigating spatial patterns of climate change, biodiversity, and ecosystem health.
  • Sustainability: Applying GIS to monitor and support sustainable development initiatives.
  • Health and epidemiology: Utilizing spatial data to track disease spread, healthcare accessibility, and public health risks.
  • Spatial planning: Enhancing land-use planning, regional development, and resource allocation through GIS.
  • Built environment and urban planning: Supporting smart city development, infrastructure optimization, and housing policies.
  • Disaster risk management: Developing spatial models to assess and mitigate risks related to natural and human-induced disasters.
  • Hydrological modeling: Analyzing water resources, flood risk, and watershed management through GIS techniques. It also includes enhancement and new development of algorithms and models to make the most of the high resolution, temporal and spatial data streams generated.
  • Mobility and transportation: Optimizing transportation networks, traffic flow analysis, and sustainable mobility planning, with a special interest in micromobility.
  • Conflicts and war: Utilizing GIS to study conflict zones, humanitarian responses, and geopolitical dynamics to assess their social and environmental impacts.

Collaboration

We work closely with other research groups within our department, faculty, and university. This collaboration allows us to conduct research across multiple disciplines, ensuring that location and spatial data remain essential in scientific studies. Our partnership with the Remote Sensing and Earth Observation group strengthens GIS research and ensures that spatial science contributes to solving global challenges and advancing geospatial intelligence.

Examples of research projects

Spatial is special: from AI to GeoAI for urban sustainability

INTEGRAL: Intelligent geo-technologies for resilient agriculture adaptation to climate change in Lao PDR

GIS and Health: Enhancing Disease Surveillance and Intervention through Spatial Epidemiology

Nature-based solutions and multiple ecosystem services in the urban landscape

 

See all researchers, research projects and more from the GIS Centre in the LU Research Portal 

Main GIS researchers