• Computational Mechanics
• Civil Engineering Computations
• Structural Engineering Computations
• Mechanical Engineering Computations
• Environmental Engineering Modelling and Simulation
• Computational Geotechnics
• Predictive Maintenance and Structural Health Monitoring
• Computational Tools and Techniques for Railway Engineering
• Materials: Analysis, Design and Development
• Computational Engineering Education

Focus Areas

• Machine Learning
• Neural Networks and Physics-Informed Neural Networks (PINNs)
• Deep Learning and Convolutional Neural Networks (CNNs)
• Automated Data Analysis and Interpretion
• Machine Learning and Sensor-Based AI for Predictive Maintenance and Structural Health Monitoring
• AI Based Techniques for Pollution Monitoring
• Integration of Machine Learning and AI for Engineering Problems
• AI Systems for support of Virtual and Enhanced Reality
• Ethical, Regulatory, and Trust Issues in AI for Engineering Applications
• Integration of AI within Engineering Design and Optimization
• Hybrid AI-Optimization Approaches for Complex Engineering
• AI-Driven Material Modeling, Smart Materials, and Performance Prediction
• Adaptive Learning, Simulation-Based Training, and Knowledge Discovery

The current list of special sessions includes:

• AI-S1: Advances in Structural Uncertainty Quantification through Machine Learning
  organised by:
  Jingwen Song, School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, China
  Chao Dang, Chair for Reliability Engineering, TU Dortmund University, Dortmund, Germany
  Marcos Valdebenito, Chair for Reliability Engineering, TU Dortmund University, Dortmund, Germany
  Pengfei Wei School of Power and Energy, Northwestern Polytechnical University, Xi’an, China
  Michael Beer Institute for Risk and Reliability, Leibniz University Hannover, Hannover, Germany
  

  Engineering structures are inherently subject to various uncertainties, including geometric variations and stochastic external loads, which can significantly impact their performance and, in extreme cases, lead to failure. Structural uncertainty quantification (UQ) encompasses methods such as uncertainty modeling, simulation, propagation, reliability analysis, sensitivity analysis, and optimization under uncertainty. Effectively quantifying uncertainties in complex, nonlinear, and high-dimensional engineering structures remains a significant challenge.

  Recent advancements in machine learning techniques—such as Gaussian processes, polynomial chaos expansion, artificial neural networks, manifold learning and data-driven UQ frameworks—have shown promise in addressing these challenges. This session invites contributions that explore the integration of machine learning with structural UQ. The scope is quite wide, including the development of machine learning-assisted models and methodologies tailored for strongly nonlinear and high-dimensional structures; approaches to handle multiple sources of uncertainties in both time-independent and time-dependent structures; techniques for managing scenarios involving small failure probabilities.

  We welcome contributions that tackle real-world challenges and present machine learning theories within disciplines such as civil engineering, aerospace engineering, construction engineering, mechanical engineering, automobile engineering, and related fields.

  This activity is organized under auspices of the Committee on Probability and Statistics in Physical Sciences (C(PS)²) of the Bernoulli Society for Mathematical Statistics and Probability

• AI-S2: PINNs in in Engineering Applications
  organised by:
  Johannes Gebert, High-Performance Computing Center, Stuttgart Germany
  Lukas Striefler, Technical University Hamburg, Germany
  Benjamin Schnabel, High-Performance Computing Center Stuttgart Germany
  

  Physics-Informed Neural Networks (PINNs) are an emerging computational approach that integrates the underlying physical laws into neural network approximations. Exploring PINNs aims to evaluate their potential for solving academic and real-world problems where traditional numerical methods might be limited. PINNs provide a flexible framework for accurately modeling systems and phenomena across various engineering domains by embedding residuals of partial differential equations directly into the loss function of neural networks. The scope of this conference special session includes assessing their effectiveness in enhancing predictive accuracy and expanding the possibilities for analysis and optimization in engineering applications.

• AI-S3: Neural Networks-Based Deep Learning for Next-Generation Engineering Optimization
  organised by:
  Majid Movahedi Rad, Széchenyi István University, Hungary
  Raffaele Cucuzza, Politecnico of Turin, Italy
  Marco Domaneschi, Politecnico of Turin, Italy
  Muayad Habashneh, Széchenyi István University, Hungary
  Hamed Fathnejat, Basque Center for Applied Mathematics, Spain
  

  This session invites researchers to explore the integration of state-of-the-art deep learning techniques and neural networks into engineering optimization. It focuses on both theoretical advancements and real-world applications, aiming to bridge computational intelligence with traditional engineering challenges. Topics of interest include, but are not limited to, structural analysis, seismic design, material behavior prediction, and infrastructure health monitoring. We particularly welcome submissions that showcase novel frameworks, enhanced simulation accuracy, and case studies that seamlessly incorporate physical constraints into AI models. This session will serve as a catalyst for interdisciplinary collaboration, pushing the boundaries of engineering through transformative advancements in AI.

• AI-S4 Ethics of AI - How Engineers Earn Trust
  organised by:
  Johannes Gebert, High-Performance Computing Center, Stuttgart Germany
  Luka Polson, The Catholic University of Zagreb, Croatia
  

  The special session on the Ethics of AI - How Engineers Earn Trust explores the ethical challenges and responsibilities associated with integrating AI technologies into engineering practices, focusing on the role of trust from both ethical and epistemic perspectives. Trust is fundamental to adopting and responsible use of AI systems, as it shapes the relationship between engineers, users, and society. Ethical concerns such as fairness, accountability, and transparency are critical to building trust, ensuring that AI technologies align with human values, and promoting societal well-being.

  From an ethical standpoint, trust requires that AI systems operate fairly, non-discriminatively, and align with ethical norms. Additionally, engineers bear a moral responsibility to design transparent, explainable, and fair systems, thereby fostering trustworthiness. Moreover, to mitigate bias and inaccuracy, engineers must also rigorously assess AI systems' data sources and epistemic presumptions.

  This special session seeks to bring together researchers to discuss frameworks for ethical and epistemic AI implementations in engineering, share case studies, and develop best practices that ensure safe, fair, and responsible AI deployment. By fostering interdisciplinary dialogue, the session will contribute to shaping AI advancements that are technically effective, trustworthy, and aligned with human values.

• AI-S5 Innovative Methods for Structural Design and Optimization of Structures and Infrastructures
  organised by:
  Dr. Raffaele Cucuzza, Department of Structural and Geotechnical Engineering, Politecnico of Turin, Torino, Italy, and College of Civil Engineering, Henan University of Technology, Zhengzhou, Henan Province, China
  Dr. Majid Movahedi Rad, Department of Structural and Geotechnical Engineering, Széchenyi István University, Győr, Hungary
  Prof. Marco Domaneschi, Department of Structural and Geotechnical Engineering, Politecnico of Turin, Torino, Italy, and International Institute for Urban Systems Engineering, Southeast University, Sipailou, Nanjing, China
  Prof. Giuseppe Carlo Marano, Department of Structural and Geotechnical Engineering, Politecnico of Turin, Torino, Italy
  

  This special session is focused on presenting a comprehensive range of advanced techniques for designing, optimizing, and modeling new structures or innovative and optimized retrofitting systems. It aims to present the latest advancements in the field of structural engineering by integrating various computer-aided design (CAD) tools, simulation techniques, and innovative approaches. These techniques enable the designers and engineers to overcome the limitations of traditional design methods and achieve better results in terms of structural efficiency and sustainability. Specifically, contributions in the following research areas are strongly encouraged:

  • Single and multi-criteria strategies;
  • New multi-disciplinary and multi-objective approaches involving environmental aspects within the design;
  • Structural shape, sizing, and topology optimization;
  • Reliability‐based design;
  • Numerical modelling and simulation;
  • Optimal identification procedure for structural control devices and/or earthquake mitigation systems;
  • Computer‐aided analysis and design, algorithms, and software development;
  • Optimization through parametric analysis and form-finding techniques of spatial structures;
  • Optimized management strategy for the resilience assessment of infrastructural networks.
• AI-S6 Multiscale, Multiphysics and Risk Analyses
  organised by:
  Professor Jung-Wuk Hong, Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, Republic of Korea
  Professor Jinho Lee, Department of Ocean Engineering, Pukyong National University, Republic of Korea
  

  Recent advances in computational mechanics, enhanced by AI technology, have facilitated the study of complex systems where multiple physical processes interact across different scales, often requiring rigorous risk analysis. This session explores advanced computational methods that integrate multiscale and multiphysics modeling with uncertainty quantification and risk assessment. Emphasizing both physics-based and AI-driven approaches, it aims to enhance predictive capabilities and decision-making in engineering applications. Topics span civil, mechanical, and aerospace engineering. By bringing together experts from diverse disciplines, this session seeks to advance innovative methodologies that improve reliability and efficiency in computational mechanics.

• AI-S7 New Trends in Applications of Machine Learning for Structural Optimization
  organised by:
  Prof. Weisheng Zhang, Dalian University of Technology, China
  Prof. Dong Li, Dalian University of Technology, China
  Prof. Jian Zhang, Northeastern University, China
  

  In recent years, machine learning (ML) has emerged as a powerful tool in engineering optimization, particularly in structural optimization, encompassing topology optimization, shape optimization, material distribution optimization, and multi-objective optimization. Traditional optimization methods often rely on computationally expensive numerical simulations, whereas ML techniques—such as deep neural networks, reinforcement learning, Bayesian optimization, and generative adversarial networks (GANs)—offer data-driven solutions that enhance the efficiency of structural optimization processes. This session encourages interdisciplinary research, fostering the integration of machine learning with computational mechanics, civil engineering, aerospace engineering, mechanical engineering, and related fields. We welcome contributions on theoretical advancements, algorithm development, and engineering applications, aiming to push the boundaries of innovation in structural optimization.

  This special session invites contributions exploring the latest advancements in machine learning for structural optimization, including but not limited to:

  • Deep learning frameworks for structural optimization
  • Applications of generative adversarial networks (GANs) in shape and topology optimization
  • Integration of reinforcement learning and Bayesian optimization in engineering design
  • Neural network-accelerated solvers for computational mechanics
  • Machine learning-based optimization techniques with embedded physical constraints
  • Intelligent approaches to multi-objective and nonlinear complex engineering problems