Working Group – RESILTRON – Self-adaptive Intelligent Socio-Technical System Digital Twin for Continuous Resilience Operationalization
Decision making for national and international emergency management and crisis response is driven by established risk assessment and management theories, models and tools. Risk assessment requires an identification of threats, vulnerabilities and consequences with certain assumptions and in specific operating scenarios that can result in limited prediction capability and unreliable decision support. Since systemic threats, such as the recent COVID-19 pandemic, are largely uncertain and unpredictable, threat quantification is difficult and conservatively assigning higher probabilities to rare threat scenarios may result in risk management solutions that are prohibitively expensive. For this reason, community resources are mostly spent on risk mitigation measures aiming at preventing or minimizing the impacts of specifically known risks, but only provide limited support for poorly characterized or complex systemic threats.
Based on the emerging paradigm of Digital Twins (i.e., a detailed, holistic and run-time model of the system under analysis set in its surrounding environment), this WG pushes this concept at the edge by envisioning a cognitive system requiring minimum human intervention based on transparent AI-enabled design that is able to autonomously “understand, learn and reason” about complex STS phenomena and provide time-boxed recommendations to match high level resilience goals in Real-Time (RT).
Emanuele Bellini (University of Campania)
Pietro Liò (University of Cambridge)
Bruria Adini (Tel Aviv University)
Franco Bagnoli (university of Florence)
Igor Linkov (Us Army Corps of Engineering)
Francesco Flammini (Mälardalen University)
Ernesto Damiani (University of Milan)
Stefano Marrone (University of Campania)
Marco Caporuscio (Linnaeus University)
Yamir Moreno (University of Zaragoza)