Artificial intelligence (AI) is rapidly transforming the way complex engineering systems are modeled, optimized, and controlled. While data-driven methods have achieved remarkable success in perception and prediction tasks, their application to real-world physical systems remains limited by challenges such as poor generalization, limited interpretability, and unreliable extrapolation beyond the training domain.

To address these challenges, Physics-guided AI has emerged as a promising paradigm that integrates physical knowledge with data-driven machine learning. By embedding governing equations, conservation laws, domain knowledge, and first-principles into learning framework, Physics-guided AI enables more effective, interpretable, reliable and data-efficient solutions for complex engineering systems.

The purpose of this Special Issue is to present the latest theoretical advances and practical applications in Physics-guided AI in modeling, control, optimization, and autonomous decision making in intelligent engineering systems, including but not limited to smart energy systems, smart transportation, robotics and cyber-physical systems. We welcome original research articles, review papers, and emerging perspectives that bridge physical principles and modern AI techniques.

The scope includes, but is not limited to:

• Physical knowledge enhanced prediction, perception, and state estimation for complex systems;
  • Hybrid modeling combining first-principles and data-driven methods for intelligent systems;
  • Reinforcement learning and data-driven control for complex dynamical systems;
  • Model-based, data-driven, and simulation-assisted learning for decision-making under uncertainty;
  • Learning-based optimization and control for large-scale interconnected systems;
  • System identification, parameter estimation, and data-driven calibration of dynamic systems;
  • Safe, reliable, and uncertainty-aware machine learning for engineering applications;
  • Multi-scale and multi-physics modeling, simulation, and surrogate modeling for complex systems;
  • Digital twin technologies for monitoring, forecasting, optimization, and predictive maintenance;
  • Learning-based methods for autonomous decision-making in cyber-physical systems;
  
  

All manuscripts submitted to the special issue will be subjected to peer review. Prospective authors should submit an electronic copy of their completed manuscript to https://mc03.manuscriptcentral.com/cai with “Special Issue on Physics-guided AI for Modeling, Control and Optimization” marked in the cover letter.

Important Date

Manuscript Due: Dec. 30, 2026

Guest Editor

Assoc. Prof. Yu Yang,

School of Automation Science and Engineering, Xi’an Jiaotong University, China

E-mail: yangyu21@xjtu.edu.cn