Intelligent Modeling, Predictive Control, and Decision-Making for Multi-Energy Transportation Systems

Dear Colleagues,

The global transition toward sustainable mobility is fundamentally reshaping transportation systems across all domains. Green marine vessels, electric vehicles, electrified railways, and next-generation aircraft are increasingly reliant on complex multi-energy power systems that integrate fuel cells, batteries, supercapacitors, and other novel energy sources. This paradigm shift introduces unprecedented challenges in system dynamics, durability, and operational efficiency. The core of these challenges lies in the cooperative modeling, prediction, control, and decision-making for these heterogeneous systems under real-world constraints.

Key issues such as the coupled degradation of fuel cells and batteries, accurate forecasting of highly dynamic propulsion loads, and the distributed coordination of multi-energy power systems demand solutions that go beyond traditional siloed approaches. The integration of data-driven artificial intelligence (AI) with physics-based models offers a transformative pathway. Techniques ranging from deep learning for state prediction and reinforcement learning for adaptive control to digital twins for system-level validation are proving critical for developing robust, efficient, and intelligent next-generation transportation platforms.

This Topic aims to compile cutting-edge research and comprehensive reviews that address the intersection of advanced informatics and multi-energy transportation systems engineering. We seek contributions that present novel methodologies, theoretical frameworks, high-fidelity simulations, and experimental validations focused on enhancing the performance, longevity, safety, and intelligence of electric and hybrid-electric transportation. We encourage submissions that demonstrate a system’s perspective, fostering cross-pollination of ideas between maritime, automotive, rail, and aerospace applications.

Areas of interest for this Topic include, but are not limited to, the following:

Detailed modeling and digital twin development for fuel cells and batteries; coupled degradation modeling, state-of-health (SOH) estimation, and remaining useful life (RUL) prediction for hybrid energy storage systems; physics-informed machine learning and hybrid models for vehicle and vessel dynamics, aerodynamics, and hydrodynamics; short-term and long-term forecasting of driving cycles, speed, torque, and power demand using AI; uncertainty quantification and robust forecasting for critical components in transportation power systems; distributed and decentralized cooperative control strategies for multi-stack fuel cell systems and multi-pack battery storage systems; adaptive and model predictive control for integrated power and propulsion management in ships, aircraft, and trains; reinforcement learning and deep reinforcement learning for real-time energy management strategies; robust and fault-tolerant control schemes to ensure system safety under component failure or extreme conditions; multi-objective optimization of energy consumption, component degradation, and trip time for complex transportation tasks; AI-powered energy and power routing algorithms for marine and aerospace hybrid electric systems; vehicle-to-grid (V2G) decision-making for coordinated charging, grid support, and resource pooling; hierarchical and federated learning architectures for collaborative learning across transportation fleets while preserving data privacy; task planning and re-planning under uncertainty for autonomous electric vehicles and vessels; cybersecurity and resilience strategies for the cyber–physical systems of connected electric transportation; co-simulation and hardware-in-the-loop (HIL) testing platforms for validating control and management strategies; lightweight AI algorithm deployment on embedded systems for real-time onboard decision-making; lifecycle analysis and techno-economic modeling of advanced multi-energy transportation systems; real-time simulation and testing platform architecture for multi-energy controller validation and performance evaluation; intelligent decision support system for fault detection and emergency operation modes.

We invite researchers and practitioners from academia, national laboratories, and industry to submit their original work to this Topic. By bringing together diverse perspectives, this collection aims to chart the course for the intelligent, efficient, and reliable multi-energy transportation systems of the future.

Dr. Yuji Zeng
Dr. Qinjin Zhang
Dr. Tianhao Qie
Dr. Xin Wang
Prof. Dr. Herbert Ho-Ching Iu
Dr. Grzegorz Karoń
Topic Editors