Measuring resilience: Leveraging Computational Methods and GIS Data for AI Decision-Making Tools

Luigi Pintacuda, Silvio Carta

Research output: Chapter in Book/Report/Conference proceedingChapter


With the growing frequency of global crises, ranging from the climate crisis to wars, resilience has become a crucial topic for investigation. While simple systems may be analysed with relative ease, complex systems necessitate a more comprehensive approach that takes into account their totality. As academics working in the built environment sector, our studies have focused on the most complex systems in this sector: communities, cities, and the wider urban environment. Urban resilience should be evaluated through a complex intersection and understanding of various factors that can be grouped into four main categories: Management, Economic Environment, Social Environment, and Physical Environment. In our case, our specific contribution focuses on the latter of these: How does the physical environment, including its layout, proximity, and redundancy of features, impact resilience from the scale of a small community to that of a large megalopolis? Our studies attempt to overcome human biases in assessing the physical environment through the design and testing of digital tools. We analyse GIS data, aerial photos, and other available data using computational methods, AI, and ML to explore beyond what the human eye can perceive, enabling us to investigate, visualise, predict, and suggest modifications to cities and urban environments that promote more resilient and sustainable development, capable of absorbing the impact of current and future crises and improving people's lives.
Original languageEnglish
Title of host publicationResilient Urbanism
EditorsGihan Karunaratne
PublisherTaylor & Francis Group
Publication statusAccepted/In press - 2024


  • resilience
  • Urban areas
  • AI artificial intelligence
  • GIS
  • Urban Analysis


Dive into the research topics of 'Measuring resilience: Leveraging Computational Methods and GIS Data for AI Decision-Making Tools'. Together they form a unique fingerprint.

Cite this