From Fiction to Fission: Generating Risk-Centric Causal Networks for Complex Risk Analysis

Thursday, January 22, 2026, from 11:00 a.m. to 12 p.m. (EST, UTC-5)
This webinar will be delivered as a LinkedIn Live event.

RSVP on LinkedIn

This webinar demonstrates how Hellixia can automatically generate Risk-Centric Causal Networks (RCCNs) from heterogeneous knowledge sources and apply them to advanced risk modeling and analysis.

Participants will see how generative AI can transform both hypothetical scenarios and detailed scientific or technical research into coherent, analyzable causal risk structures suitable for simulation and decision support.

Part I — Nuclear Crisis Scenario from A House of Dynamite

The first segment explores an RCCN automatically derived from the 17-minute nuclear missile crisis depicted in the 2025 political thriller A House of Dynamite. Hellixia converts a fictional yet plausible crisis narrative into an operational RCCN that captures:

• Late mid-flight missile detection and compressed decision windows
• Failure of interceptor attempts
• Conflicting attribution signals with cyber or stealth ambiguity
• High-pressure decision-making under uncertainty (retaliate vs. absorb the strike)
• Human, institutional, and communication breakdowns
• Multiple outcome pathways driven by unresolved decisions in the film

This narrative-to-RCCN transformation illustrates how AI can turn unstructured storytelling into structured causal networks that support Bayesian simulation and “what-if” analysis of critical decisions.

Part II — Small-Break Loss-of-Coolant Accident (SBLOCA) in Marine Nuclear Power Plants

The second example focuses on automatically generating an RCCN from a recent academic study, A Cause Analysis Model of Nuclear Accidents in Marine Nuclear Power Plants Based on the Perspective of a Socio-Technical System. Hellixia distills the article’s findings into an integrated RCCN that models:

Multi-Domain Threat Structure

• Technical failures (e.g., pump 2 failure, valve malfunctions, loss of water sources)
• Human and environmental risks (operator isolation failure, severe sea states, offshore remoteness)
• Organizational and policy factors (inadequate procedures, weak regulatory oversight, policy gaps)

Preventive and Mitigating Barriers

• Redundant design, testing, and surveillance
• Passive safety systems that extend grace time
• Psychological support programs
• Emergency communication protocols
• International support and information-sharing mechanisms

Consequences Modeled

• Onboard fatalities, radiation exposure, and marine contamination
• Long-term power loss and economic damage
• Maritime operational disruptions
• Public panic and global reputational impacts
• Subsequent regulatory tightening and policy reform

This case study shows how AI can extract layered socio-technical interactions from dense academic literature and convert them into a complete RCCN that enables risk quantification, scenario analysis, and decision evaluation.

About the Presenters

Lionel Jouffe

Dr. Lionel Jouffe is co-founder and CEO of France-based Bayesia S.A.S. Lionel holds a Ph.D. in Computer Science from the University of Rennes and has worked in Artificial Intelligence since the early 1990s. While working as a Professor/Researcher at ESIEA, Lionel started exploring the potential of Bayesian networks. After co-founding Bayesia in 2001, he and his team have been working full-time on the development of BayesiaLab. Since then, BayesiaLab has emerged as the leading software package for knowledge discovery, data mining, and knowledge modeling using Bayesian networks. It enjoys broad acceptance in academic communities, business, and industry.

Stefan Conrady

Stefan Conrady has over 20 years of experience in decision analysis, analytics, market research, and product strategy, having worked with Mercedes-Benz, BMW Group, Rolls-Royce Motor Cars, and Nissan across North America, Europe, and Asia. As Managing Partner of Bayesia USA and Bayesia Singapore, he is widely recognized as a thought leader in applying Bayesian networks to research, analytics, and decision-making. Together with his business partner, Dr. Lionel Jouffe, he co-authored Bayesian Networks & BayesiaLab — A Practical Introduction for Researchers, an influential resource now widely cited in academic literature. With their deep expertise in Bayesian networks for Key Driver Analysis and Optimization, Stefan and Lionel are highly sought-after consultants, advising global leaders such as Procter & Gamble, Coca-Cola, UnitedHealth Group, L’Oréal, the World Bank, and many of the world’s largest market research firms.