This special issue addresses decision-making in complex industrial systems facing dynamic uncertainty through artificial intelligence and optimization techniques. The issue seeks research combining AI methods such as reinforcement learning, generative AI, and digital twins with operations research and optimization approaches to manage manufacturing, supply chains, healthcare, and other sectors dealing with demand fluctuations and disruptions.
The special issue welcomes both theoretical and practical contributions demonstrating how AI-driven methodologies can improve decision-making under uncertainty. Particular emphasis is placed on interdisciplinary research with clear industrial applicability and the adoption of open science practices including data and code sharing to enhance reproducibility.