International workshop focuses on AI for critical infrastructure

On August 4, LLNL researchers Felipe Leno da Silva and Ruben Glatt hosted the AI for Critical Infrastructure workshop at the 33rd International Joint Conference on Artificial Intelligence (IJCAI) in Jeju, South Korea. Professors Wencong Su (University of Michigan – Dearborn) and Yi Wang (University of Hong Kong) joined them in organizing the workshop focused on exploring AI opportunities and challenges in this globally important domain.

“Given the fast pace of advances in AI, collaboration with industry and academia is required to remain in the forefront of AI developments. Hosting this workshop at a top AI conference not only supports keeping LLNL updated about external advances but also promotes forging new partnerships,” said Leno da Silva, who serves as technical outreach coordinator for the Lab’s Data Science Institute.

Critical infrastructures (CIs) encompass essential public services such as transportation, energy, telecommunications, hospitals, and information technology networks. CIs are widely considered to be fundamental to societal well-being and security. From planning to operation, the integration of AI into every aspect of CIs is paramount to enhancing the efficiency, reliability, and resilience of these intricate and multifaceted systems.

AI can optimize CI planning processes, forecast future demands, and pinpoint vulnerabilities. During operations, AI can ensure seamless functioning by quickly addressing disruptions and mitigating risks such as cyberattacks or natural disturbances intensified by climate change. Despite the potential benefits, the application and evaluation of AI in CIs are complex due to their critical impact on society. Ensuring the safety and trustworthiness of increasingly autonomous AI systems in CIs is crucial, necessitating robust frameworks to safeguard public trust and infrastructure integrity.

“The Department of Energy and LLNL have a strong interest in safe and reliable infrastructure that operates efficient and without interruptions. Based on our past work that connects energy and transportation infrastructure components, we wanted to build a home for AI applications in that space. With this workshop, we are following a trend that connects application areas with the AI community at major conferences to stimulate discussion and cross-collaboration to drive innovation,” said Ruben Glatt, director of the Lab’s Center for Advanced Signal and Image Sciences.

The workshop featured 15 peer-reviewed papers across a range of topics such as deadlock detection for railways, neural networks for electronic health records, and reinforcement learning for voltage control. Keynote speakers were Tao Chen (Southeast University, China) on management and pricing methods for demand-side resources in energy CI and Wei Lin (University of Hong Kong) on trustworthy machine learning techniques for power system optimization.

André Artelt (University of Bielefeld, Germany) and collaborators won the workshop’s Best Paper Award for “A Toolbox for Supporting Research on AI in Water Distribution Networks.” The team’s paper introduces a Python toolbox for complex scenario modeling and generation to facilitate access to challenging problems from the drinking water domain.