AI-Driven Decision Making under Uncertain Environments: Theory, Methods, and Industrial Applications

Editors

  • Hyun-Jung Kim, KAIST
  • Shu-Kai Fan, National Taipei University of Technology
  • Fugee Tsung, Hong Kong University of Science and Technology
  • Thomas Volling, Technical University Berlin
  • Jang Ho Kim, Korea University
  • Dong-Young Lim, Ulsan National Institute of Science and Technology

Description

Recent advances in artificial intelligence (AI), optimization, and data-driven analytics are fundamentally transforming decision-making processes in complex systems operating under uncertainty. Modern industrial and service systems, including manufacturing, logistics, supply chains, transportation, energy, and healthcare, increasingly face dynamic and stochastic environments characterized by demand fluctuations, disruptions, incomplete information, evolving system states, and operational risks. To effectively manage such complexity, there is growing interest in intelligent decision-making methodologies that integrate learning, prediction, optimization, simulation, and adaptation. In particular, emerging technologies such as reinforcement learning, foundation models, generative AI, agentic AI, digital twins, and hybrid AI-optimization frameworks are enabling the development of more autonomous, adaptive, and data-driven operational systems. Despite these advances, significant challenges remain regarding scalability, robustness, interpretability, real-time implementation, and the successful deployment of AI-driven decision-making approaches in real-world industrial environments.

This Special Issue aims to provide a platform for cutting-edge research on AI-driven decision making under uncertain environments, with particular emphasis on methodologies and real-world applications that combine AI techniques with operations research, optimization, simulation, control, and industrial engineering approaches. The issue welcomes both theoretical and applied contributions addressing uncertainty-aware intelligent decision-making across a broad range of industrial and service systems.

The Special Issue is organized in conjunction with APIEMS 2026. Selected high-quality papers presented at the conference will be invited to submit extended versions for possible publication in the Special Issue. The Special Issue will also be open to general submissions from researchers worldwide. All submitted manuscripts will undergo the standard rigorous peer-review process of the International Journal of Production Research.

The Special Issue particularly encourages interdisciplinary studies demonstrating practical relevance, industrial applicability, and managerial insights for complex decision-making problems under uncertainty. To foster transparency, reproducibility, and cumulative scientific progress, open science practices such as the sharing of (synthetic) data, code, models, prompts, and comprehensive replication materials are strongly encouraged and highly valued.

Potential topics

  • AI-driven decision-making under uncertainty
  • Production planning and scheduling in stochastic and dynamic environments
  • Reinforcement learning for uncertain industrial systems
  • Stochastic optimization and robust operational strategies
  • AI-enabled statistical quality control and process improvement
  • Hybrid AI and optimization approaches for uncertain environments
  • Data-driven optimization and prescriptive analytics
  • AI-enhanced supply chain and logistics management under disruptions
  • Real-time and adaptive decision-making systems
  • Simulation-based optimization and digital twins under uncertainty
  • Agentic AI and autonomous industrial systems
  • Explainable and trustworthy AI for operational decision-making
  • AI for resilient and sustainable operations
  • Industrial applications and case studies of AI-driven decision systems